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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    That
    0.79
    この
    0.75
    This
    0.72
    this
    0.69
    นี้
    0.69
    കാരം
    0.68
     Hopefully
    0.67
     That
    0.67
    The
    0.66
     This
    0.66
    POSITIVE LOGITS
    ורי
    0.63
    各有
    0.62
     sido
    0.60
     wasser
    0.59
     xhrObj
    0.59
     له
    0.58
     உள்ளன
    0.58
    _{+}
    0.57
     имеются
    0.56
    weit
    0.56
    Act Density 0.009%

    No Known Activations