INDEX

Explanations

bone formation and types

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

connecting words like "and" when they appear in scientific papers, particularly in results or statistics sections.

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

The neuron consistently activates on numeric tokens (counts, percentages, measurements) in scientific or data‐heavy text.

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

 加盟

-1.46

 сейчас

-1.46

 теперь

-1.40

 に関する

-1.34

に行って

-1.34

iſ

-1.26

 sogar

-1.25

ഏ

-1.24

 ücretsiz

-1.23

 pierws

-1.21

POSITIVE LOGITS

 huiles

1.41

 épices

1.41

 also

1.39

 this

1.29

was

1.27

 groen

1.24

 fabricants

1.20

 tirs

1.20

 composés

1.19

Activations Density 0.004%

bone formation and types

connecting words like "and" when they appear in scientific papers, particularly in results or statistics sections.

The neuron consistently activates on numeric tokens (counts, percentages, measurements) in scientific or data‐heavy text.

No Comments

No Known Activations

bone formation and types

connecting words like "and" when they appear in scientific papers, particularly in results or statistics sections.

The neuron consistently activates on numeric tokens (counts, percentages, measurements) in scientific or data‐heavy text.

No Comments

No Known Activations