INDEX
    Explanations
    New Auto-Interp
    Negative Logits
     national
    -1.41
    national
    -1.16
    shape
    -1.09
     shape
    -1.08
     nationaux
    -1.03
     Shape
    -0.98
     nazionale
    -0.98
     nacionales
    -0.96
     nasional
    -0.91
     nacional
    -0.90
    POSITIVE LOGITS
    posedge
    0.58
     createContext
    0.50
     convert
    0.50
     boc
    0.49
     Kita
    0.46
     cref
    0.46
     tennis
    0.43
     aku
    0.43
    Convert
    0.43
    amarin
    0.43
    Act Density 0.068%

    No Known Activations