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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    cod
    -0.80
    TX
    -0.78
    Ore
    -0.77
    Tx
    -0.76
    ILLE
    -0.73
    ighed
    -0.72
    ruary
    -0.71
    pps
    -0.70
    animal
    -0.67
    atron
    -0.67
    POSITIVE LOGITS
     reapp
    0.68
    zbollah
    0.66
     patches
    0.65
    notations
    0.64
     faint
    0.63
     patch
    0.62
     leaps
    0.60
     changes
    0.60
     Emblem
    0.59
     sheds
    0.59
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.