INDEX

Explanations

section headers

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

This neuron activates on the delimiters and decorative lines of block comments (e.g. the “/”, “/”, and repeated “*” lines) in source files.

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

 caufe

-0.96

 abstrak

-0.95

 rése

-0.92

 reprises

-0.91

 asfal

-0.91

 faciles

-0.90

 signifikan

-0.90

 kompet

-0.90

 guerres

-0.90

 Fazit

-0.90

POSITIVE LOGITS

 Krzysz

0.98

 sottile

0.85

性は

0.84

and

0.84

lawayo

0.81

itosan

0.81

crivez

0.80

 sağlar

0.80

二年

0.79

 semicirc

0.79

Activations Density 0.004%

section headers

This neuron activates on the delimiters and decorative lines of block comments (e.g. the “/”, “/”, and repeated “*” lines) in source files.

No Comments

No Known Activations

section headers

This neuron activates on the delimiters and decorative lines of block comments (e.g. the “/”, “/”, and repeated “*” lines) in source files.

No Comments

No Known Activations

section headers

This neuron activates on the delimiters and decorative lines of block comments (e.g. the “/*”, “*/”, and repeated “*” lines) in source files.

No Comments

No Known Activations

section headers

This neuron activates on the delimiters and decorative lines of block comments (e.g. the “/*”, “*/”, and repeated “*” lines) in source files.

No Comments

No Known Activations

This neuron activates on the delimiters and decorative lines of block comments (e.g. the “/”, “/”, and repeated “*” lines) in source files.

This neuron activates on the delimiters and decorative lines of block comments (e.g. the “/”, “/”, and repeated “*” lines) in source files.