INDEX

Explanations

Microsoft documentation or code

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

This neuron detects numeric literals (number tokens) in code or text.

oai_token-act-pair · o4-mini Triggered by @jyhe0408

assignment operators or equals signs in code and structured data.

oai_token-act-pair · claude-4-5-sonnet Triggered by @jyhe0408

assignments or key–value pairs, especially variable/property initialization in code and attribute/value settings in markup or data.

oai_token-act-pair · gpt-5 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

Not in Any Lists

No Comments

Negative Logits

ーラ

-0.91

 eröffnet

-0.88

its

-0.86

 ofrece

-0.85

áfrica

-0.80

 nejs

-0.79

 samot

-0.79

 aluno

-0.79

 használ

-0.78

żs

-0.77

POSITIVE LOGITS

Matem

0.95

 tear

0.80

 instan

0.79

 Riviera

0.76

 rati

0.74

 tina

0.74

νος

0.73

 metastases

0.73

 знаешь

0.73

bungen

0.72

Activations Density 0.002%

Microsoft documentation or code

This neuron detects numeric literals (number tokens) in code or text.

assignment operators or equals signs in code and structured data.

assignments or key–value pairs, especially variable/property initialization in code and attribute/value settings in markup or data.

No Comments

No Known Activations