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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     همچ
    0.49
    จากการ
    0.45
    dari
    0.44
    จาก
    0.42
     από
    0.41
    from
    0.39
     дар
    0.38
     دار
    0.38
     تک
    0.37
     كه
    0.37
    POSITIVE LOGITS
     s
    0.48
     thế
    0.42
     ('
    0.39
     Oll
    0.39
     of
    0.39
     Thế
    0.39
    /:
    0.38
     premises
    0.38
     :(
    0.38
     below
    0.37
    Act Density 0.000%

    No Known Activations