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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    mble
    -0.68
    dylib
    -0.65
    dule
    -0.63
    ctuary
    -0.62
     Jindal
    -0.61
    earable
    -0.61
    terday
    -0.61
    ority
    -0.60
    reement
    -0.60
     Dise
    -0.60
    POSITIVE LOGITS
     continuity
    0.72
     surg
    0.69
     modem
    0.69
     reversal
    0.67
    itted
    0.66
    bach
    0.66
    idental
    0.64
     Herz
    0.63
     zipper
    0.63
     revers
    0.62
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.