INDEX

Explanations

cough or coughing

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

medical symptoms related to coughing in clinical contexts.

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

The neuron flags occurrences of the word “cough” (and its variants) in the document.

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

New Auto-Interp

Configuration

google/gemma-scope-27b-pt-res/layer_10/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

–

-2.88

訁

-2.67

 dieß

-2.59

鉝

-2.56

-2.53

が

-2.44

ᡨ

-2.42

så

-2.42



-2.31

 所以

-2.27

POSITIVE LOGITS

2.48

 dicono

2.47

鼱

2.41

慊

2.31

 pédagog

2.28

 dédi

2.27

 değiştir

2.27

楪

2.25

 themſelves

2.22

骢

2.22

Activations Density 0.002%

cough or coughing

medical symptoms related to coughing in clinical contexts.

The neuron flags occurrences of the word “cough” (and its variants) in the document.

No Comments

No Known Activations

cough or coughing

medical symptoms related to coughing in clinical contexts.

The neuron flags occurrences of the word “cough” (and its variants) in the document.

No Comments

No Known Activations