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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     Pound
    -0.65
     cancell
    -0.57
     cac
    -0.57
     Flare
    -0.57
    ãĥ¥
    -0.57
     '
    -0.57
     embr
    -0.56
    existent
    -0.56
     Cosmetic
    -0.56
     Private
    -0.56
    POSITIVE LOGITS
    enario
    0.84
    well
    0.83
     largeDownload
    0.82
     ILCS
    0.75
    ulia
    0.72
    zona
    0.70
    river
    0.69
    esta
    0.69
     Calder
    0.68
    oples
    0.67
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.