INDEX
    Explanations
    New Auto-Interp
    Negative Logits
    Vaya
    -0.66
    Iné
    -0.62
    ]}"
    -0.56
    hyrchwyd
    -0.56
    ("}");
    -0.56
    ")));
    
    -0.55
     يتيمه
    -0.55
     tromper
    -0.55
    Ahoj
    -0.54
    mặt
    -0.54
    POSITIVE LOGITS
    Abitanti
    0.66
    ScopeManager
    0.59
    енча
    0.56
     proprietario
    0.56
     <<<<<<<<<<<<<<
    0.56
    +#+#
    0.55
    posedge
    0.55
     öne
    0.54
     uſed
    0.54
    BeginInit
    0.53
    Act Density 0.087%

    No Known Activations