INDEX

Explanations

constant modifier

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

the word "constant" when describing ongoing or continuous states, situations, or processes.

oai_token-act-pair · claude-4-5-sonnet Triggered by @bfgcn7frf5

The neuron reliably activates on the word “constant.”

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

皷

-1.83

しゃれ

-1.75

Ž

-1.64

Étymologie

-1.58

 टॉप

-1.57

ствии

-1.57

迨

-1.57

хими

-1.56

もちゃ

-1.55

蚨

-1.52

POSITIVE LOGITS

2.08

ine

1.89

);

1.82

؛

1.78

1.74

!”

1.73

an

1.71

 воздей

1.66

_;

1.66

𖧵

1.64

Activations Density 0.013%

constant modifier

the word "constant" when describing ongoing or continuous states, situations, or processes.

The neuron reliably activates on the word “constant.”

No Comments

No Known Activations

constant modifier

the word "constant" when describing ongoing or continuous states, situations, or processes.

The neuron reliably activates on the word “constant.”

No Comments

No Known Activations