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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    _pwd
    -0.06
    遑
    -0.06
    슭
    -0.06
    =image
    -0.06
    趺
    -0.06
    쬘
    -0.06
    舞蹈
    -0.06
    负责人
    -0.06
    뻑
    -0.06
    髂
    -0.06
    POSITIVE LOGITS
    ﹻ
    0.08
    بارك
    0.07
    phot
    0.07
     arriv
    0.07
     unve
    0.07
    gather
    0.07
    ôme
    0.07
     Dabei
    0.06
     NEED
    0.06
     internal
    0.06
    Act Density 0.001%

    No Known Activations