INDEX

Explanations

medical imaging brain

np_acts-logits-general · gemini-2.5-flash-lite

URLs and file paths in technical documents.

oai_token-act-pair · claude-3-7-sonnet-20250219 Triggered by @neilrathi

This neuron fires on numeric sequences (e.g. version numbers, package “from”/“resolved” URLs, integrity hashes) in JSON‐style dependency metadata.

oai_token-act-pair · o4-mini Triggered by @jyhe0408

New Auto-Interp

Configuration

google/gemma-scope-27b-pt-res/layer_22/width_131k

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits



-1.09



-1.06

 crise

-1.05

 claras

-1.05

 его

-1.00

gée

-0.97

ückt

-0.96

colhead

-0.96

 correctes

-0.96

all

-0.95

POSITIVE LOGITS

and

1.36

 here

1.13

 andato

1.04

好像

1.02

 tampaknya

1.00

嘴唇

0.99

 ovviamente

0.98

 arrivato

0.96

 recomienda

0.94

 těchto

0.94

Activations Density 0.000%

medical imaging brain

URLs and file paths in technical documents.

This neuron fires on numeric sequences (e.g. version numbers, package “from”/“resolved” URLs, integrity hashes) in JSON‐style dependency metadata.

No Comments

No Known Activations

medical imaging brain

URLs and file paths in technical documents.

This neuron fires on numeric sequences (e.g. version numbers, package “from”/“resolved” URLs, integrity hashes) in JSON‐style dependency metadata.

No Comments

No Known Activations