INDEX
    Explanations

    occurrences of the abbreviation "NN" related to neural networks

    New Auto-Interp
    Negative Logits
     lizenz
    -0.43
    Effect
    -0.39
    ized
    -0.38
    -0.37
    ulco
    -0.37
    César
    -0.37
    uszcz
    -0.36
    										
    -0.36
     Ră
    -0.36
    ised
    -0.36
    POSITIVE LOGITS
     NN
    0.67
     HttpNotFound
    0.60
    msgTypes
    0.60
     nn
    0.58
    NN
    0.56
     ProtoMessage
    0.56
    nnn
    0.54
     esternos
    0.51
    endregion
    0.50
    nn
    0.49
    Act Density 0.010%

    No Known Activations