INDEX

Explanations

paralysis and paralyzed muscles

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

This neuron detects references to paralysis or being paralyzed in medical and technical contexts.

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

The neuron detects mentions of paralysis or being paralyzed.

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

</h3>

-2.39

´

-2.31

But

-2.14

 gewiß

-1.97

浤

-1.91

 nuevos

-1.89

 Their

-1.88

⢇

-1.83

鹮

-1.82

 andare

-1.81

POSITIVE LOGITS

瘓

2.63

}$

2.52

</b>

2.31

 туалет

1.94

婠

1.91

}{

1.91

⡪

1.88

揠

1.86

麺

1.84

 belangrijke

1.84

Activations Density 0.005%

paralysis and paralyzed muscles

This neuron detects references to paralysis or being paralyzed in medical and technical contexts.

The neuron detects mentions of paralysis or being paralyzed.

No Comments

No Known Activations

paralysis and paralyzed muscles

This neuron detects references to paralysis or being paralyzed in medical and technical contexts.

The neuron detects mentions of paralysis or being paralyzed.

No Comments

No Known Activations