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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    enance
    -0.95
    ĸļ
    -0.76
    haar
    -0.72
    ppo
    -0.69
    ionage
    -0.68
     Foley
    -0.68
     Gry
    -0.66
     Rica
    -0.65
    interstitial
    -0.65
     Gree
    -0.64
    POSITIVE LOGITS
    FP
    0.69
    lux
    0.68
    gal
    0.66
    tarians
    0.66
    team
    0.65
    Lot
    0.65
     board
    0.65
    gres
    0.61
    inel
    0.61
    iasco
    0.61
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.