INDEX
    Explanations
    New Auto-Interp
    Negative Logits
    _yes
    -0.07
     cinema
    -0.07
     igen
    -0.07
     här
    -0.07
     CI
    -0.07
    =yes
    -0.07
     Screen
    -0.07
    Ports
    -0.07
    енных
    -0.07
     баст
    -0.07
    POSITIVE LOGITS
     prob
    0.08
    lems
    0.08
    0.08
    istler
    0.08
     ecc
    0.07
     לד
    0.07
     proximal
    0.07
     metaph
    0.07
    teva
    0.07
    rían
    0.07
    Act Density 0.000%

    No Known Activations