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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    鼗
    0.89
     confirmé
    0.87
     crore
    0.87
    RUPTION
    0.87
    ের
    0.86
     afferm
    0.86
    ون
    0.85
    azione
    0.83
    ів
    0.82
     cérémonie
    0.82
    POSITIVE LOGITS
    da
    0.79
    cb
    0.70
    但他
    0.70
    rtl
    0.68
    lobal
    0.68
     {};
    0.67
    bool
    0.67
    div
    0.66
    bass
    0.66
    См
    0.66
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.