INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     immigrant
    0.44
    ActiveClass
    0.43
    criminal
    0.43
    ગો
    0.42
    zett
    0.40
    groupBy
    0.39
    中です
    0.39
     scarce
    0.38
    фон
    0.38
     scarcely
    0.38
    POSITIVE LOGITS
     ابتدا
    0.50
     começo
    0.47
     Town
    0.46
     chair
    0.45
     madeira
    0.45
     cam
    0.43
     iniz
    0.43
     Beaufort
    0.43
    fontsize
    0.43
    0.43
    Act Density 0.020%

    No Known Activations