INDEX
    Explanations
    New Auto-Interp
    Negative Logits
     bele
    -0.08
    erb
    -0.07
     lata
    -0.07
     بناء
    -0.07
    -0.07
     yees
    -0.07
    -0.07
     وقت
    -0.07
     ub
    -0.07
    *time
    -0.07
    POSITIVE LOGITS
    .ceil
    0.09
    ceil
    0.08
    σ
    0.08
     smallest
    0.08
    (svg
    0.08
    0.08
     Ches
    0.07
     medal
    0.07
    contro
    0.07
    inh
    0.07
    Act Density 0.005%

    No Known Activations