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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    aucus
    -0.64
     upside
    -0.62
    BUG
    -0.62
    âĢ¢âĢ¢
    -0.62
    DEV
    -0.61
    ratulations
    -0.61
     Stub
    -0.61
    REDACTED
    -0.61
    BALL
    -0.60
    1200
    -0.60
    POSITIVE LOGITS
    gan
    0.73
    heed
    0.72
    undai
    0.72
    activity
    0.69
    angan
    0.67
    agan
    0.67
    itiz
    0.66
    lins
    0.63
    iday
    0.62
    obal
    0.62
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.