INDEX
    Explanations
    New Auto-Interp
    Negative Logits
     versi
    2.52
     reckons
    2.51
    2.50
     sebab
    2.38
     sayfası
    2.36
     campaigner
    2.33
     calendario
    2.30
     günü
    2.28
     ialah
    2.27
     calendário
    2.24
    POSITIVE LOGITS
    7
    1.73
    6
    1.53
    8
    1.52
    4
    1.44
    3
    1.42
    5
    1.38
    9
    1.27
    0
    0.98
    rinsic
    0.98
    1
    0.91
    Act Density 0.040%

    No Known Activations