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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     Swanson
    -0.73
     Canaveral
    -0.73
    kaya
    -0.72
    izon
    -0.68
    kinson
    -0.66
    arial
    -0.64
     libertarian
    -0.62
     Jinping
    -0.62
     Hollande
    -0.61
    ufficient
    -0.61
    POSITIVE LOGITS
    tackle
    0.75
    idding
    0.69
    case
    0.69
    ds
    0.67
     Puzz
    0.65
    aunts
    0.65
    cases
    0.65
    Demand
    0.64
    erenn
    0.64
    rez
    0.64
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.