INDEX

Explanations

diseases and syndromes

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

medical conditions and diseases introduced with parentheses that include their abbreviations.

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

This neuron detects the defining pattern of a medical acronym—specifically the closing parenthesis of an acronym followed by a copula (“is” or “is an”) that introduces its definition.

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

the

-1.97

-1.59

 this

-1.50

 PORTRAIT

-1.48

 AGRIC

-1.47

 THOUGH

-1.45

chosen

-1.44

vieto

-1.43

 each

-1.41

POSITIVE LOGITS

谆

1.74

 esetén

1.62

 olyan

1.58

 powiedzieć

1.57

↵

1.54

 dotyczące

1.54

 szczeg

1.53

 establecer

1.51

بيرة

1.48

 Bretaña

1.48

Activations Density 0.788%

diseases and syndromes

medical conditions and diseases introduced with parentheses that include their abbreviations.

This neuron detects the defining pattern of a medical acronym—specifically the closing parenthesis of an acronym followed by a copula (“is” or “is an”) that introduces its definition.

No Comments

No Known Activations

diseases and syndromes

medical conditions and diseases introduced with parentheses that include their abbreviations.

This neuron detects the defining pattern of a medical acronym—specifically the closing parenthesis of an acronym followed by a copula (“is” or “is an”) that introduces its definition.

No Comments

No Known Activations