INDEX
    Explanations
    New Auto-Interp
    Negative Logits
     BTN
    -0.62
     Markle
    -0.61
     IPC
    -0.58
     peric
    -0.58
     Klu
    -0.58
     Audrey
    -0.57
    ----</
    -0.56
    -0.56
     Lauter
    -0.56
    Rij
    -0.55
    POSITIVE LOGITS
    typedef
    3.12
     typedef
    1.85
     typename
    0.95
     propOrder
    0.90
     onOptions
    0.78
    NESOTA
    0.77
    typename
    0.77
    EditorBrowsable
    0.71
    Cyfeiriadau
    0.71
     Besten
    0.70
    Act Density 0.039%

    No Known Activations