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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ensing
    -0.77
    xxxxxxxx
    -0.69
    ulia
    -0.67
    usat
    -0.66
    aqu
    -0.66
     datas
    -0.62
    nyder
    -0.62
    unknown
    -0.62
     IPM
    -0.61
    pg
    -0.61
    POSITIVE LOGITS
    odynam
    0.69
    ermanent
    0.69
    76561
    0.63
    selves
    0.61
    Merit
    0.60
     Au
    0.60
     palate
    0.59
     Emin
    0.59
     Sandwich
    0.59
     Bohem
    0.59
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.