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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    hedral
    -0.69
    ItemImage
    -0.67
    Magikarp
    -0.66
    pair
    -0.64
    ollah
    -0.62
    AUD
    -0.61
     pals
    -0.60
    pins
    -0.59
    pointers
    -0.59
    manship
    -0.59
    POSITIVE LOGITS
    ploy
    0.76
    ictional
    0.75
    uci
    0.74
    aez
    0.71
    eting
    0.69
    ostic
    0.68
    ocument
    0.67
    ocaly
    0.67
    ifact
    0.66
    ause
    0.63
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.