INDEX
    Explanations

    people's names

    New Auto-Interp
    Negative Logits
    Widget
    -0.07
     MEMORY
    -0.07
     Robert
    -0.06
    -0.06
    -0.06
    ştir
    -0.06
     Пос
    -0.06
     TextAlign
    -0.06
    asma
    -0.06
     Metrics
    -0.06
    POSITIVE LOGITS
     гром
    0.07
    itemid
    0.06
    0.06
     Dal
    0.06
    irq
    0.06
     scar
    0.06
    _weight
    0.06
     Spar
    0.06
     gyro
    0.06
    hk
    0.06
    Act Density 0.012%

    No Known Activations