INDEX

Explanations

doxorubicin

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

This neuron detects chemical and drug names, particularly "doxorubicin" and related scientific terminology.

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

The neuron is strongly activated by the subword “ub,” as found repeatedly in the drug name “doxorubicin.”

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

and

-2.34

 from

-2.30

nipeg

-1.85

$}

-1.81

 time

-1.81

pasti

-1.80

 henvisninger

-1.80

تاح

-1.74

millimeters

-1.70

vaná

-1.69

POSITIVE LOGITS

2.13

嘿嘿

1.78

to

1.75

赶紧

1.68

1.67

 ไม่

1.63

1.62

是

1.57

re

1.55

 verhind

1.55

Activations Density 0.174%

doxorubicin

This neuron detects chemical and drug names, particularly "doxorubicin" and related scientific terminology.

The neuron is strongly activated by the subword “ub,” as found repeatedly in the drug name “doxorubicin.”

No Comments

No Known Activations

doxorubicin

This neuron detects chemical and drug names, particularly "doxorubicin" and related scientific terminology.

The neuron is strongly activated by the subword “ub,” as found repeatedly in the drug name “doxorubicin.”

No Comments

No Known Activations