INDEX
    Explanations
    New Auto-Interp
    Negative Logits
    ëren
    0.96
    klop
    0.95
    0.91
    ،
    0.90
    ток
    0.88
    ками
    0.86
    ك
    0.86
    MainNav
    0.82
    кло
    0.81
     явля
    0.80
    POSITIVE LOGITS
    a
    1.27
    et
    1.06
    n
    1.06
    t
    1.02
    و
    1.00
    id
    0.95
    is
    0.94
    il
    0.93
    ie
    0.91
    i
    0.88
    Act Density 0.000%

    No Known Activations