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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    toNumber
    0.81
    也
    0.78
     criticize
    0.71
     (>
    0.70
    もしくは
    0.68
    一定
    0.66
    תוך
    0.66
    而后
    0.64
     hạng
    0.64
    ({\
    0.63
    POSITIVE LOGITS
     ابن
    0.75
     Bias
    0.75
     ancho
    0.68
     Inicio
    0.66
     aula
    0.66
     mieszkań
    0.65
    Bias
    0.65
     অবাক
    0.65
     gazebo
    0.64
     भाज
    0.64
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.