INDEX

Explanations

ischemic stroke and injury

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

medical terms related to ischemia and reperfusion injuries in scientific literature.

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

The neuron activates on mentions of “ischemic” (and related ischemia contexts) in medical descriptions.

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

-2.53

-2.38

-2.20

-2.11

he

-1.97

ys

-1.90

榇

-1.89

!!!!!!!

-1.86

 focuses

-1.85

しやすい

-1.85

POSITIVE LOGITS

</b>

1.98

☎️

1.91

</em>

1.89

 diğer

1.80

</h5>

1.80

TWO

1.68

 अन्य

1.67

jadikan

1.66

↵↵

1.63

 Pokud

1.63

Activations Density 0.045%

ischemic stroke and injury

medical terms related to ischemia and reperfusion injuries in scientific literature.

The neuron activates on mentions of “ischemic” (and related ischemia contexts) in medical descriptions.

No Comments

No Known Activations

ischemic stroke and injury

medical terms related to ischemia and reperfusion injuries in scientific literature.

The neuron activates on mentions of “ischemic” (and related ischemia contexts) in medical descriptions.

No Comments

No Known Activations