INDEX

Explanations

resistance to

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

The neuron identifies descriptions of resistance or tolerance to various conditions or substances, particularly in scientific and technical contexts.

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

The neuron detects adjectives of resistance or tolerance (e.g. “resistant,” “robust,” “immune,” “tolerant”) immediately followed by the preposition “to.”

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

-1.77

‘

-1.69

但他

-1.68

for

-1.61

his

-1.59

粼

-1.55

けれ

-1.55

 television

-1.53

現状

-1.53

 invoked

-1.52

POSITIVE LOGITS

︓

1.74

Więcej

1.71

 každý

1.70



1.69

伈

1.68

 všetky

1.67

蒾

1.67

 certaines

1.67

 expédi

1.66

 them

1.60

Activations Density 0.066%

resistance to

The neuron identifies descriptions of resistance or tolerance to various conditions or substances, particularly in scientific and technical contexts.

The neuron detects adjectives of resistance or tolerance (e.g. “resistant,” “robust,” “immune,” “tolerant”) immediately followed by the preposition “to.”

No Comments

No Known Activations

resistance to

The neuron identifies descriptions of resistance or tolerance to various conditions or substances, particularly in scientific and technical contexts.

The neuron detects adjectives of resistance or tolerance (e.g. “resistant,” “robust,” “immune,” “tolerant”) immediately followed by the preposition “to.”

No Comments

No Known Activations