INDEX

Explanations

medical trial results

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

abbreviations or acronyms of medical studies, trials, and research publications.

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

The neuron is triggered by numeric tokens—especially study years, dosages, sample sizes, and other quantifying numbers in clinical research text.

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

着她

-0.89

THAT

-0.86

リ

-0.85

wak

-0.84

Bang

-0.84

ш

-0.83

Buy

-0.81

WRITING

-0.81

 qPCR

-0.79

POSITIVE LOGITS

Crítica

1.04

谞

1.01

Недостатки

0.98

Sugges

0.97

纐

0.95

┰

0.93

面白かった

0.91

Sonntag

0.91

Teléfono

0.91

ㄉ

0.90

Activations Density 0.257%

medical trial results

abbreviations or acronyms of medical studies, trials, and research publications.

The neuron is triggered by numeric tokens—especially study years, dosages, sample sizes, and other quantifying numbers in clinical research text.

No Comments

No Known Activations

medical trial results

abbreviations or acronyms of medical studies, trials, and research publications.

The neuron is triggered by numeric tokens—especially study years, dosages, sample sizes, and other quantifying numbers in clinical research text.

No Comments

No Known Activations