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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ĸļ
    -0.76
    href
    -0.71
    ĨĴ
    -0.67
     hours
    -0.65
    abama
    -0.64
    ãĤ¤ãĥĪ
    -0.63
    ¥µ
    -0.61
     Discipline
    -0.61
     differently
    -0.61
     Watts
    -0.61
    POSITIVE LOGITS
    rings
    0.72
    Pal
    0.71
    achu
    0.70
    amas
    0.69
    án
    0.69
    faces
    0.68
     PAL
    0.67
    prints
    0.67
    ItemTracker
    0.66
    marked
    0.65
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.