INDEX

Explanations

medical, biological, and chemical concepts

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

This neuron identifies scientific and medical terminology, particularly in research contexts.

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

The neuron selectively fires on high-level scientific or technical nouns (multi-syllabic domain-specific terms) such as “medical,” “neuro,” “plant,” “molecular,” “chemical,” “clinical,” “statistical,” etc.

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

と

-1.40

は

-1.39

、

-1.31

。

-1.26

を

-1.23

are

-1.22

などの

-1.21

etc

-1.20

など

-1.20

が

-1.17

POSITIVE LOGITS

為に

1.84

 voordelen

1.59

ようになりました

1.47

ところに

1.45

 skóra

1.42

 voorwaarden

1.39

こともあり

1.38

 duża

1.36

 aandacht

1.34

久し

1.34

Activations Density 0.294%

medical, biological, and chemical concepts

This neuron identifies scientific and medical terminology, particularly in research contexts.

The neuron selectively fires on high-level scientific or technical nouns (multi-syllabic domain-specific terms) such as “medical,” “neuro,” “plant,” “molecular,” “chemical,” “clinical,” “statistical,” etc.

No Comments

No Known Activations

medical, biological, and chemical concepts

This neuron identifies scientific and medical terminology, particularly in research contexts.

The neuron selectively fires on high-level scientific or technical nouns (multi-syllabic domain-specific terms) such as “medical,” “neuro,” “plant,” “molecular,” “chemical,” “clinical,” “statistical,” etc.

No Comments

No Known Activations