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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     trasporto
    0.83
    ınızı
    0.82
     offending
    0.81
    くれる
    0.81
     водой
    0.81
    ணி
    0.80
    د
    0.79
    دة
    0.78
    واد
    0.78
    ح
    0.76
    POSITIVE LOGITS
     Söz
    0.95
     ప్రి
    0.94
    Desen
    0.92
     Mortal
    0.90
    Detection
    0.89
     дека
    0.89
    assertions
    0.87
     wonderland
    0.87
    Listener
    0.86
    饺
    0.86
    Act Density 0.000%

    No Known Activations