Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    :
    0.64
    .
    0.63
    ,
    0.60
    ;
    0.53
    ።
    0.52
                              
    0.51
     :
    0.50
     ('
    0.50
     eines
    0.50
     -
    0.50
    POSITIVE LOGITS
    économie
    0.52
     انتہائی
    0.51
     progression
    0.49
    élément
    0.49
     উজ্জ্বল
    0.48
    üksek
    0.48
    ifferent
    0.48
    équilibre
    0.47
    ff
    0.47
    ні
    0.46
    Act Density 0.137%

    No Known Activations