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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     kebanyakan
    0.87
    িয়াম
    0.86
     kebakaran
    0.83
    ל
    0.82
    plugins
    0.81
     yılları
    0.79
    دي
    0.78
    えて
    0.78
    يام
    0.77
    ווה
    0.77
    POSITIVE LOGITS
    s
    1.12
     Nij
    0.94
    sby
    0.86
    పై
    0.83
    nä
    0.83
     Phy
    0.82
    них
    0.80
    тельной
    0.80
     Naras
    0.79
     osm
    0.79
    Act Density 0.000%

    No Known Activations