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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    "(
    0.76
     Enzym
    0.75
    Smiling
    0.73
     perempt
    0.71
    𝟏
    0.70
     Sereth
    0.69
    residual
    0.69
    "});
    0.69
     "!
    0.69
     bistro
    0.69
    POSITIVE LOGITS
    峄
    0.74
    ra
    0.68
     la
    0.68
    ig
    0.64
    lsen
    0.64
     Wars
    0.63
    ymi
    0.61
     Image
    0.61
    ânt
    0.60
    ropower
    0.60
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.