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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     상태
    0.47
    伙伴
    0.46
     сумма
    0.45
     మ్యాచ్
    0.45
     akka
    0.45
     суток
    0.44
     मुद्दा
    0.44
    larda
    0.44
    Truthy
    0.44
    小伙伴
    0.44
    POSITIVE LOGITS
    does
    0.44
    rops
    0.43
    drops
    0.42
    ِه
    0.41
    hate
    0.41
     laisse
    0.40
    .
    0.38
    ly
    0.38
    ட்
    0.38
    ."
    0.38
    Act Density 0.018%

    No Known Activations