INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    s
    1.60
    m
    1.58
    زيد
    1.29
    1.18
     eficiencia
    1.17
     empec
    1.14
    غيرة
    1.12
    1.11
    ból
    1.09
    \,\
    1.08
    POSITIVE LOGITS
    1.69
    .
    1.59
     a
    1.30
     is
    1.22
     v
    1.14
     on
    1.14
    मा
    1.11
    ite
    1.10
     be
    1.09
     he
    1.09
    Act Density 0.000%

    No Known Activations