INDEX
    Explanations
    New Auto-Interp
    Negative Logits
     última
    -0.07
    _center
    -0.06
     cánh
    -0.06
    /banner
    -0.06
    _unsigned
    -0.06
    _corner
    -0.06
    (avg
    -0.06
    _fixed
    -0.06
    ncpy
    -0.06
    -0.06
    POSITIVE LOGITS
    ,col
    0.07
    PERSON
    0.07
              
    0.07
                            
    0.07
    слід
    0.07
    0.07
    0.07
    ↵                        ↵
    0.07
     Feel
    0.06
    					
    0.06
    Act Density 0.001%

    No Known Activations