# Inside LLM — See inside a language model

> See inside a language model (iPhone/iPad app by Wonmo Seong.)

- Source: https://appshunter.io/ios/app/inside-llm/id6819051390 (this page in markdown: same URL + `.md`)
- Developer: [Wonmo Seong](https://appshunter.io/developer/1625011193)
- Category: Education, Developer Tools
- Price: Free with in-app purchases
- Age rating: 4+
- Requires: iOS 17.0 · 160 MB
- Languages: American English
- Released: 2026-11-04
- Data updated: 2026-11-13

## What is Inside LLM?

Ever wondered what your keyboard is doing when it suggests the next word? Inside LLM runs a real language model on your iPhone or iPad and draws every step of its thinking.

This is not a chatbot and not an online service. The app contains its own transformer inference engine, written from scratch in Swift on Apple's Accelerate framework, and computes the full network on your device after every keystroke so that every intermediate number can be shown.

Type anything and see:

- Suggestions: the three most probable next words, exactly as a predictive keyboard would show them, with their real probabilities.
- Signal through the network: six layers lighting up as the forward pass runs.
- Attention: a heatmap of which earlier words each token is reading from, for any of the 72 attention heads, or averaged.
- Neurons: all 3,072 MLP neurons in each layer, firing for your last word.
- Logit lens: what the model would guess if it stopped after layer 0, 1, 2, and how that guess sharpens or changes as it goes deeper.
- Weights: every one of the model's 76 weight tensors, rendered as a zoomable heatmap of the actual numbers learned in training.
- Steps: a six-step walkthrough of one forward pass (tokenize, embed, attend, MLP, stack, softmax) using your own words as the example.

Everything runs locally. No account, no analytics, no ads. Nothing you type leaves the device. An optional tip jar in About lets you support development; tips unlock nothing and every feature is free.

The model is DistilGPT2 (Hugging Face, Apache 2.0), an 82-million-parameter distilled GPT-2 trained on 2019 web text. Its suggestions are shown for learning purposes and can be wrong or dated. The engine's output is checked against an independent reference implementation in the app's test suite, and the method is described in an open technical report.

## Pricing and in-app purchases

Base price: Free.

**One-time purchases**

| Purchase | Price | Type |
| --- | --- | --- |
| Small tip | $1.99 | one-time |
| Medium tip | $4.99 | one-time |
| Large tip | $9.99 | one-time |


## Is Inside LLM safe?

Not enough ratings yet to assess Inside LLM.

## Is Inside LLM legit?

Inside LLM appears legitimate, with a few gaps. The AppsHunter Legitimacy Score for Inside LLM is 70 out of 100 points across 7 verification signals from App Store and developer data.


## Version history (last 2 releases)

### 1.1 — 2026-11-11

Orch Neural Network is now Inside LLM. New: an optional tip jar in About (tips unlock nothing; everything stays free). Cleaner labels throughout.

### 1.0 — 2026-11-04

No release notes.

## More apps by Wonmo Seong

- [Title Capitalizr](https://appshunter.io/ios/app/title-capitalizr/id1625011191)
- [Electronify: Electron Orbitals](https://appshunter.io/ios/app/electronify-electron-orbitals/id6446613861)
- [Atomizer AR: Quantum Chemistry](https://appshunter.io/ios/app/atomizer-ar-quantum-chemistry/id6449015706)
- [UC ClassFinder](https://appshunter.io/ios/app/uc-classfinder/id6460809805)
- [Asperger's Guide for Autism](https://appshunter.io/ios/app/aspergers-guide-for-autism/id6466399113)
- [OpticALLY 3D Scan: Persona](https://appshunter.io/ios/app/optically-3d-scan-persona/id6468313142)

All apps by Wonmo Seong: https://appshunter.io/developer/1625011193

---

*Data collected daily from the US App Store and indexed by [AppsHunter](https://appshunter.io/). User reviews are verbatim App Store reviews. Ratings, prices and chart positions refresh continuously; this snapshot is from 2026-11-13.*
