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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     Awareness
    -0.07
    犯罪
    -0.07
    =false
    -0.07
    كبر
    -0.06
    DAO
    -0.06
     określon
    -0.06
    -good
    -0.06
    ery
    -0.06
     France
    -0.06
    allowed
    -0.06
    POSITIVE LOGITS
    /Subthreshold
    0.08
    묄
    0.07
     telecommunications
    0.07
     lowest
    0.07
     características
    0.07
    鸤
    0.07
    igy
    0.07
     misunder
    0.06
     seiz
    0.06
     debuted
    0.06
    Act Density 0.001%

    No Known Activations