INDEX

Explanations

counting patients and cases

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

The neuron detects text about medical/scientific studies with patient counts and cases.

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

The neuron detects numerical counts and statistical figures (numbers and digits) in the 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

and

-1.21

not

-1.00

儘

-0.96

or

-0.93

an

-0.92

 regardé

-0.90

様の

-0.88

بدأ

-0.87

 februari

-0.87

 protagon

-0.87

POSITIVE LOGITS

のうち

1.28

 antaranya

1.17

out

1.12

 מתוך

1.09

 diantaranya

1.09

 apiece

1.07

そこから

1.06

cellaneous

1.06

ὁ

1.05

中有

1.03

Activations Density 0.061%

counting patients and cases

The neuron detects text about medical/scientific studies with patient counts and cases.

The neuron detects numerical counts and statistical figures (numbers and digits) in the text.

No Comments

No Known Activations

counting patients and cases

The neuron detects text about medical/scientific studies with patient counts and cases.

The neuron detects numerical counts and statistical figures (numbers and digits) in the text.

No Comments

No Known Activations