INDEX

Explanations

remission

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

nouns related to states or conditions, particularly medical or technical terms like "remission," "spectrum," or "domain."

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

The neuron fires on individual content-bearing nouns—especially less common or technical terms—rather than on function words or common everyday words.

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

 through

-1.63

 from

-1.43

 while

-1.36

 though

-1.31

 helped

-1.29

 called

-1.27

to

-1.24

but

-1.23

 each

-1.23

the

-1.20

POSITIVE LOGITS

 में

1.50

TIMES

1.31

gitto

1.30

ETHER

1.28

 OGSÅ

1.27

 befind

1.24

nonatomic

1.23

iedenis

1.23

cenie

1.23

 obliter

1.23

Activations Density 0.252%

remission

nouns related to states or conditions, particularly medical or technical terms like "remission," "spectrum," or "domain."

The neuron fires on individual content-bearing nouns—especially less common or technical terms—rather than on function words or common everyday words.

No Comments

No Known Activations

remission

nouns related to states or conditions, particularly medical or technical terms like "remission," "spectrum," or "domain."

The neuron fires on individual content-bearing nouns—especially less common or technical terms—rather than on function words or common everyday words.

No Comments

No Known Activations