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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks indicating dialogue or quotations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Code, math, or symbols

    np_acts-logits-general · gemini-2.0-flash

    code, math, and diverse languages

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ,
    -0.74
    .
    -0.72
    <eos>
    -0.71
     and
    -0.69
    ↵↵
    -0.69
    -
    -0.68
     al
    -0.67
     for
    -0.63
     ma
    -0.63
     in
    -0.63
    POSITIVE LOGITS
    IntoConstraints
    1.32
     BoxDecoration
    1.23
     Normdatei
    1.22
     للمعارف
    1.13
    出版年
    1.13
    RectangleBorder
    1.13
    __":
    1.11
     iſt
    1.09
     EconPapers
    1.08
     itſelf
    1.06
    Act Density 0.284%

    No Known Activations