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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     and
    1.25
    را
    0.96
     by
    0.94
     of
    0.93
    ورك
    0.92
     (
    0.92
    ra
    0.92
    ak
    0.89
    يان
    0.89
    volle
    0.88
    POSITIVE LOGITS
    त
    1.31
    स
    1.29
    ت
    1.29
    る
    1.20
    >
    1.17
    س
    1.16
    ס
    1.16
    I
    1.14
    م
    1.13
    อ
    1.09
    Act Density 0.000%

    No Known Activations