INDEX
    Explanations
    New Auto-Interp
    Negative Logits
     bam
    -0.08
     Vect
    -0.07
     developmental
    -0.07
    eck
    -0.07
     CI
    -0.07
     Prospect
    -0.07
     miserable
    -0.06
     fullWidth
    -0.06
     گی
    -0.06
     lớ
    -0.06
    POSITIVE LOGITS
     den
    0.09
     Den
    0.08
    Buffers
    0.07
    .den
    0.07
     DEN
    0.07
    .N
    0.07
    Terminal
    0.07
    0.07
    typename
    0.07
    نی
    0.06
    Act Density 0.044%

    No Known Activations