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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     멋
    0.73
     grotes
    0.65
    )}^
    0.63
     забезпечення
    0.63
    .??.??"]
    0.63
     larceny
    0.63
     tumult
    0.61
     prü
    0.61
    ريخ
    0.61
     birefring
    0.61
    POSITIVE LOGITS
    Diabetes
    1.10
    diabetes
    0.98
     Diabetes
    0.96
     diabetes
    0.94
    Can
    0.91
    Does
    0.86
    I
    0.84
    He
    0.83
    can
    0.83
    does
    0.83
    Act Density 0.001%

    No Known Activations