INDEX
    Explanations

    class attributes and properties

    New Auto-Interp
    Negative Logits
     tess
    0.39
    лета
    0.38
     currents
    0.37
     highs
    0.37
     fels
    0.36
     pool
    0.36
     phen
    0.36
     foss
    0.36
     korzyst
    0.36
     native
    0.35
    POSITIVE LOGITS
    Programm
    0.43
     Programm
    0.42
     זיי
    0.41
     женщины
    0.39
     വനി
    0.39
     человек
    0.38
    programm
    0.38
    链路
    0.38
     അറ
    0.38
     якія
    0.38
    Act Density 0.004%

    No Known Activations