INDEX
    Explanations
    New Auto-Interp
    Negative Logits
    appro
    -0.07
     }))
    -0.07
     männer
    -0.07
    andest
    -0.06
    	request
    -0.06
    ющ
    -0.06
    -house
    -0.06
     //------------------------------------------------
    -0.06
     ==============================================================
    -0.06
     infected
    -0.06
    POSITIVE LOGITS
     Surf
    0.06
     priv
    0.06
    řej
    0.06
     tide
    0.06
    .RED
    0.06
    .pixel
    0.06
     Lind
    0.06
     Jeff
    0.06
     WEEK
    0.05
     addr
    0.05
    Act Density 0.014%

    No Known Activations