INDEX
    Explanations
    New Auto-Interp
    Negative Logits
     meu
    -0.07
     beraber
    -0.07
    >Your
    -0.07
     imaging
    -0.07
     █████
    -0.06
     decrement
    -0.06
    -0.06
     کودکان
    -0.06
     teamwork
    -0.06
    "F
    -0.06
    POSITIVE LOGITS
     Stripe
    0.08
    stripe
    0.07
     Currency
    0.07
    esthesia
    0.07
     SCH
    0.06
    _dat
    0.06
    	tile
    0.06
     stripe
    0.06
    -pos
    0.06
     Square
    0.06
    Act Density 0.001%

    No Known Activations