INDEX
    Explanations
    New Auto-Interp
    Negative Logits
    Ջ
    0.61
    Afghanistan
    0.57
    Afghan
    0.56
     افغانستان
    0.55
    ensureEqual
    0.54
    Asian
    0.53
    Georgian
    0.53
     কাশ্মীর
    0.53
     եր
    0.53
     ወይም
    0.52
    POSITIVE LOGITS
     Brazilian
    2.33
     Brasil
    2.30
     Brazil
    2.20
     brasile
    2.13
     brazilian
    2.09
    Brazilian
    2.08
     brasil
    2.06
     Brasile
    2.03
     brasileiros
    2.03
     brasileiro
    2.02
    Act Density 0.040%

    No Known Activations