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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     pse
    -0.70
    uphem
    -0.68
    GoldMagikarp
    -0.68
    zin
    -0.67
    gans
    -0.65
    dash
    -0.65
     Absolute
    -0.64
     seism
    -0.64
    atorium
    -0.64
     Electricity
    -0.62
    POSITIVE LOGITS
    staff
    0.71
    lez
    0.70
    ultz
    0.69
    court
    0.68
    pread
    0.67
    ework
    0.66
    ppa
    0.65
     Predators
    0.65
    rely
    0.64
    itton
    0.64
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.