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

    Neuronpedia

    INDEX
    Explanations

    multiple different patterns including numbers, items in a list, and code related words.

    oai_token-act-pair · gemini-2.0-flash

    programming and french

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     onAnimation
    -0.91
     ModelExpression
    -0.86
     comuniques
    -0.74
    dymyr
    -0.70
     فريبيس
    -0.70
    UIControlState
    -0.69
    ConstraintMaker
    -0.66
    WebElementEntity
    -0.65
     gynhyrchwyd
    -0.65
     surla
    -0.65
    POSITIVE LOGITS
    reggio
    0.52
     아니라
    0.47
     referenties
    0.47
    Населення
    0.46
     Daarna
    0.45
    indirizzo
    0.43
     wezen
    0.42
    怎么做
    0.42
    LikeLike
    0.41
    gulier
    0.41
    Act Density 1.823%

    No Known Activations