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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     birçok
    0.58
     veľ
    0.57
     mathrm
    0.57
     Nhiều
    0.56
    이라는
    0.56
     många
    0.55
    raulic
    0.54
     여러
    0.54
     किंग
    0.54
     Кі
    0.54
    POSITIVE LOGITS
     সেগুলো
    0.75
     it
    0.75
     ඒවා
    0.71
     them
    0.71
     mereka
    0.69
     них
    0.69
     họ
    0.67
     ಅದನ್ನು
    0.67
    它们
    0.64
     feedback
    0.63
    Act Density 0.001%

    No Known Activations