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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    nam
    -0.77
    iard
    -0.72
     Gloria
    -0.72
    inea
    -0.72
    Downloadha
    -0.71
     graz
    -0.71
    vern
    -0.68
     Gaul
    -0.67
     Champ
    -0.66
    naires
    -0.66
    POSITIVE LOGITS
    layout
    0.69
    ructose
    0.68
    ogun
    0.67
    attribute
    0.66
    510
    0.64
     congr
    0.64
    aker
    0.63
    tie
    0.63
    WASHINGTON
    0.62
    âĹı
    0.62
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.