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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     Canal
    -0.67
    henko
    -0.66
    illus
    -0.66
    azel
    -0.65
    qua
    -0.64
    lass
    -0.64
    WORK
    -0.63
    umblr
    -0.62
    é¾įå
    -0.61
     Yoga
    -0.61
    POSITIVE LOGITS
    Downloadha
    0.75
    ongyang
    0.71
    opsis
    0.67
    uries
    0.62
    icides
    0.62
     disadvant
    0.62
     ç¥ŀ
    0.61
     modification
    0.61
    endish
    0.60
    anni
    0.60
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.