Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    blog or article content

    np_max-act · gemini-2.0-flash

    The neuron fires on punctuation and special tokens that mark ends of sentences or message boundaries (e.g. “?”, end-of-text markers).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8

    assistant-style, numbered-list advice and instructional guidance (self-help tips and how-to responses).

    oai_token-act-pair · gpt-5Triggered by @vetterc0
    New Auto-Interp
    Negative Logits
    ,copy
    -0.06
    237
    -0.06
     funkce
    -0.06
     definition
    -0.06
     yol
    -0.06
     گرفته
    -0.06
     checker
    -0.06
     quatre
    -0.06
     Damon
    -0.06
     dc
    -0.06
    POSITIVE LOGITS
    看着
    0.07
    .......
    0.06
     evolving
    0.06
    ulmuş
    0.06
    depart
    0.06
     вигля
    0.06
    ////////
    0.06
     Organizations
    0.06
    lığının
    0.06
     markdown
    0.06
    Act Density 0.113%

    No Known Activations