INDEX
    Explanations
    New Auto-Interp
    Negative Logits
     NullPointerException
    -0.07
    irting
    -0.07
    .addValue
    -0.07
    oslav
    -0.06
     FactoryGirl
    -0.06
     cgi
    -0.06
     crawling
    -0.06
    shirt
    -0.06
    .AddWithValue
    -0.06
     Hanna
    -0.06
    POSITIVE LOGITS
     Mn
    0.07
     acquire
    0.06
     απο
    0.06
     ####
    0.06
     gam
    0.06
     linked
    0.06
     fled
    0.06
     given
    0.06
    category
    0.06
     suffer
    0.06
    Act Density 0.020%

    No Known Activations