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

    Neuronpedia

    INDEX
    Explanations

    structures or symbols indicative of code documentation or annotations

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

    Code comments or documentation

    np_acts-logits-general · gemini-2.0-flash

    program documentation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ModelExpression
    -0.69
    IndentedString
    -0.68
    mphony
    -0.54
     createSprite
    -0.54
    HasIndex
    -0.51
    SourceChecksum
    -0.48
    mergeFrom
    -0.48
    createCanvas
    -0.48
     ویکی‌پدیا
    -0.47
     ExecuteAsync
    -0.47
    POSITIVE LOGITS
     asexual
    0.61
    ništvo
    0.59
     religieuse
    0.58
     Política
    0.57
    jerne
    0.57
     Ryzen
    0.56
    ůr
    0.55
    躇
    0.55
    ArgsConstructor
    0.54
    Życiorys
    0.54
    Act Density 0.019%

    No Known Activations