INDEX
    Explanations
    New Auto-Interp
    Negative Logits
    Maker
    -0.08
     functioning
    -0.07
     Land
    -0.07
     misc
    -0.07
     regulatory
    -0.07
     Dok
    -0.07
     apet
    -0.07
     функциони
    -0.07
    quipment
    -0.07
     temperament
    -0.07
    POSITIVE LOGITS
     đi
    0.08
    جل
    0.08
     أه
    0.08
    ाह
    0.07
     prohibit
    0.07
     Bartlett
    0.07
     overe
    0.07
     મુસ
    0.07
    žnost
    0.07
    0.07
    Act Density 0.035%

    No Known Activations