INDEX

Explanations

ex vivo, in vivo

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

scientific or technical terms, particularly those in chemistry, biology, and medical research contexts.

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

The neuron activates on distinctive multi‐syllable technical or scientific terms (e.g. “eddies,” “cyclodextrin,” “ex vivo,” “YUV,” “vagus”).

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

 Then

-2.20

</h3>

-1.98

?”

-1.96

).

-1.88

 Furthermore

-1.88

The

-1.88

}=$

-1.88

-1.87

</h6>

-1.84

”;

-1.80

POSITIVE LOGITS

 proposons

1.85

 avions

1.67

꯱

1.66

isation

1.60

ising

1.58

 appréci

1.54

 Тан

1.53

пыта

1.52

These

1.50

 первая

1.50

Activations Density 0.042%

ex vivo, in vivo

scientific or technical terms, particularly those in chemistry, biology, and medical research contexts.

The neuron activates on distinctive multi‐syllable technical or scientific terms (e.g. “eddies,” “cyclodextrin,” “ex vivo,” “YUV,” “vagus”).

No Comments

No Known Activations

ex vivo, in vivo

scientific or technical terms, particularly those in chemistry, biology, and medical research contexts.

The neuron activates on distinctive multi‐syllable technical or scientific terms (e.g. “eddies,” “cyclodextrin,” “ex vivo,” “YUV,” “vagus”).

No Comments

No Known Activations