INDEX

Explanations

chemical groups and moieties

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

chemical compounds and molecular structures in scientific text.

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

This neuron activates on tokens from chemical nomenclature (e.g. functional‐group and compound name fragments like “SH,” “phenyl,” “yl,” “ol,” “trin,” etc.), i.e. it detects chemical compound or functional‐group terms.

oai_token-act-pair · o4-mini Triggered by @jyhe0408

New Auto-Interp

Configuration

google/gemma-scope-27b-pt-res/layer_34/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

邮件

-0.83

arkar

-0.82

Relations

-0.81

点数

-0.80

 quelli

-0.79

 désign

-0.78

 librement

-0.78

訁

-0.77

身体

-0.77

𝗼

-0.76

POSITIVE LOGITS

 group

1.78

 groups

1.59

 moiety

1.56

 units

1.38

 molecules

1.14

 molecule

1.11

 unit

1.09

group

1.06

in

1.06

 entity

1.05

Activations Density 0.219%

chemical groups and moieties

chemical compounds and molecular structures in scientific text.

This neuron activates on tokens from chemical nomenclature (e.g. functional‐group and compound name fragments like “SH,” “phenyl,” “yl,” “ol,” “trin,” etc.), i.e. it detects chemical compound or functional‐group terms.

No Comments

No Known Activations

chemical groups and moieties

chemical compounds and molecular structures in scientific text.

This neuron activates on tokens from chemical nomenclature (e.g. functional‐group and compound name fragments like “SH,” “phenyl,” “yl,” “ol,” “trin,” etc.), i.e. it detects chemical compound or functional‐group terms.

No Comments

No Known Activations