INDEX

Explanations

medical conditions and industries

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

specialized terminology and jargon within professional or academic disciplines.

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

The main thing this neuron does is detect domain-specific technical jargon and specialized content terms (e.g. medical, scientific, or industry-related nouns).

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

 from

-1.41

 with

-1.30

 mondta

-1.26

if

-1.21

or

-1.21

 that

-1.20

 which

-1.20

いただけます

-1.19

ivotopis

-1.15

 Only

-1.14

POSITIVE LOGITS

 différentes

1.42

 alcune

1.30

 predominantly

1.30

 semelh

1.30

 verschillende

1.29

 diferite

1.24

 pesso

1.22

 frança

1.18

 コットン

1.16

 offiziell

1.16

Activations Density 0.315%

medical conditions and industries

specialized terminology and jargon within professional or academic disciplines.

The main thing this neuron does is detect domain-specific technical jargon and specialized content terms (e.g. medical, scientific, or industry-related nouns).

No Comments

No Known Activations

medical conditions and industries

specialized terminology and jargon within professional or academic disciplines.

The main thing this neuron does is detect domain-specific technical jargon and specialized content terms (e.g. medical, scientific, or industry-related nouns).

No Comments

No Known Activations