# Goodfire says scaling agent investigations improves neuron explanations

> Original title: We also found that scaling agent-driven investigations reliably improves our explanations, measured by simulation scores.

- Source: Goodfire
- Published: 2026-11-10T18:26:29.000Z
- Bad Influence: https://badinfluence.news/items/whzj15y5wdlp95wbxzdis4s1z
- Original: https://x.com/GoodfireAI/status/2120221571034001458

## Summary

Goodfire reports that scaling agent-driven investigations reliably improves its neuron explanations, as measured by simulation scores. It says each neuron described gives clues to the next, so its understanding of the network compounds.

## Post

We also found that scaling agent-driven investigations reliably improves our explanations, measured by simulation scores.

And each neuron we describe offers gives us clues to the next, like a crossword. Our understanding of the network compounds.

![](https://badinfluence.news/api/img-proxy?u=https%3A%2F%2Fpbs.twimg.com%2Fmedia%2FHWyKSF5akAA8KI-.jpg&mode=thumb&exp=1794528000&sig=0a551b420d41f8ba)