INDEX

Explanations

hydrophobic core; self-splicing; non-digestible; initial gut; along nerves

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

technical and scientific terms related to biology, chemistry, and cellular structures.

oai_token-act-pair · claude-3-7-sonnet-20250219

Triggered by @neilrathi

The neuron strongly responds to molecular‐biology wording—especially biomolecule names (like proteins or RNA), molecular properties (e.g. “hydrophobic”), and related technical terms.

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

Negative Logits

‎

-1.21

 Whilst

-1.05

Whilst

-0.99

 ясно

-0.98

Tome

-0.97

Vivi

-0.95

Amical

-0.94

Karol

-0.94

 ��

-0.93

 vehículos

-0.92

POSITIVE LOGITS

 intensa

0.98

itación

0.90

 especially

0.88

 τὸν

0.85

 they

0.85

tuh

0.85

siveness

0.85

 because

0.85

 τὴν

0.85

AMIENTO

0.84

Activations Density 0.057%

hydrophobic core; self-splicing; non-digestible; initial gut; along nerves

technical and scientific terms related to biology, chemistry, and cellular structures.

The neuron strongly responds to molecular‐biology wording—especially biomolecule names (like proteins or RNA), molecular properties (e.g. “hydrophobic”), and related technical terms.

No Known Activations

hydrophobic core; self-splicing; non-digestible; initial gut; along nerves

technical and scientific terms related to biology, chemistry, and cellular structures.

The neuron strongly responds to molecular‐biology wording—especially biomolecule names (like proteins or RNA), molecular properties (e.g. “hydrophobic”), and related technical terms.

No Known Activations