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

    Neuronpedia

    INDEX
    Explanations

    names/titles

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ffer
    -1.30
    hoi
    -0.99
    FFER
    -0.86
    thed
    -0.65
     hoi
    -0.63
     Wikimedijinoj
    -0.61
    ffers
    -0.59
    êmios
    -0.55
    ffa
    -0.54
     Cuerpo
    -0.51
    POSITIVE LOGITS
     متعلقه
    0.75
    DoubleQuotes
    0.69
    openzeppelin
    0.63
    AnchorStyles
    0.60
     chrétienne
    0.59
    ValueGenerated
    0.57
    AndroidJUnit
    0.57
    VersionUID
    0.56
    ServletConfig
    0.56
    cadilly
    0.54
    Act Density 0.193%

    No Known Activations