INDEX

Explanations

signs of medical conditions

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

the phrase "signs of" often found in medical or clinical contexts.

oai_token-act-pair · claude-3-7-sonnet-20250219

Triggered by @neilrathi

The neuron fires on the term “signs” (especially in the phrase “signs of …”), marking headings or mentions of clinical signs or symptoms.

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

Negative Logits

-2.17

 ferner

-1.80

姈

-1.77

×

-1.70

 ebenso

-1.66

看了一眼

-1.59

垸

-1.54

了下

-1.51

絢

-1.50

心头

-1.49

POSITIVE LOGITS

袿

1.82

 veya

1.77

已经

1.74

 alebo

1.70

 Ekonomi

1.67

兇

1.60

養

1.59

 include

1.59

 ของ

1.59

悳

1.55

Activations Density 0.033%

signs of medical conditions

the phrase "signs of" often found in medical or clinical contexts.

The neuron fires on the term “signs” (especially in the phrase “signs of …”), marking headings or mentions of clinical signs or symptoms.

No Known Activations

signs of medical conditions

the phrase "signs of" often found in medical or clinical contexts.

The neuron fires on the term “signs” (especially in the phrase “signs of …”), marking headings or mentions of clinical signs or symptoms.

No Known Activations