# Goodfire says natural-language neuron descriptions predict and activate neurons

> Original title: Neurons are predictable. We can generate short, natural language descriptions of neurons' roles. Providing the description to a judge mod...

- Source: Goodfire
- Published: 2026-11-10T18:26:25.000Z
- Bad Influence: https://badinfluence.news/items/myndqq9980pqlfs99r2bj8iau
- Original: https://x.com/GoodfireAI/status/2120221554474901957

## Summary

Goodfire says it can generate short natural-language descriptions of neurons' roles. Given to a judge model, the descriptions predict when a neuron will fire and simulate its behavior. Goodfire says the method activates neurons more strongly than anything in its corpus.

## Post

Neurons are predictable. We can generate short, natural language descriptions of neurons' roles. Providing the description to a judge model lets us predict when the neuron will fire, simulate its behavior, and activate it more strongly than anything in our corpus.

![](https://badinfluence.news/api/img-proxy?u=https%3A%2F%2Fpbs.twimg.com%2Fmedia%2FHWyKRJKbIAAUQBD.jpg&mode=thumb&exp=1794528000&sig=90d4a86a27ccfbc3)