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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    だけでなく
    0.63
     Nhiều
    0.58
    但也
    0.57
     jednotliv
    0.56
     innumerable
    0.56
     ছাড়াও
    0.56
     ebenso
    0.54
    ವಲ್ಲ
    0.54
     though
    0.53
     বটে
    0.53
    POSITIVE LOGITS
    ensatz
    0.72
     cosidd
    0.68
     sekitar
    0.68
    ipkan
    0.67
     czyli
    0.66
    つまり
    0.65
    aholic
    0.64
     από
    0.64
     intorno
    0.63
    ק
    0.63
    Act Density 0.000%

    No Known Activations