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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    STAT
    -0.72
    cipl
    -0.71
    gans
    -0.69
     Reader
    -0.68
    Students
    -0.67
    FIN
    -0.66
     Fundamental
    -0.65
    Journal
    -0.64
    execute
    -0.64
    Reader
    -0.62
    POSITIVE LOGITS
     [*]
    0.68
     Ski
    0.67
     Glacier
    0.64
    ndra
    0.64
    ée
    0.63
     lame
    0.63
    VPN
    0.63
     ads
    0.62
    asin
    0.62
     âĶĤ
    0.61
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.