INDEX

Explanations

medical findings and advice

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

descriptions of medical findings, diagnoses, or healthcare procedures in narratives.

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

The neuron fires on verbs (often past‐tense) that report findings or announcements—e.g. “discovered,” “said,” “revealed,” “gave” etc.

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

 each

-1.23

выми

-1.19

isierung

-1.19

 '../../../../

-1.16

 couver

-1.14

 jaun

-1.12

精灵

-1.11

uldig

-1.10

 verst

-1.09

vry

-1.06

POSITIVE LOGITS

 conditions

1.53

 recommend

1.40

him

1.38

إنه

1.38

 alojamientos

1.37

 alrededores

1.36

 تواند

1.30

 soggior

1.30

 acoged

1.29

 אבל

1.27

Activations Density 0.147%

medical findings and advice

descriptions of medical findings, diagnoses, or healthcare procedures in narratives.

The neuron fires on verbs (often past‐tense) that report findings or announcements—e.g. “discovered,” “said,” “revealed,” “gave” etc.

No Comments

No Known Activations

medical findings and advice

descriptions of medical findings, diagnoses, or healthcare procedures in narratives.

The neuron fires on verbs (often past‐tense) that report findings or announcements—e.g. “discovered,” “said,” “revealed,” “gave” etc.

No Comments

No Known Activations