Skip to content
MIT Technology Review · AI

Goodfire releases Silico, a mechanistic interpretability tool for debugging LLMs

This startup’s new mechanistic interpretability tool lets you debug LLMs

Goodfire released Silico, letting engineers inspect and adjust LLM parameters during training. It maps neurons and pathways; one Qwen 3 neuron triggered trolley-problem-style outputs. Pricing is case-by-case, and the post does not disclose rates.

Why it matters: Silico lets engineers inspect and adjust model parameters during training and map neurons and circuits.

Read the original ↗Export Markdown