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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     certs
    -0.84
     encount
    -0.75
    ayson
    -0.74
     RELE
    -0.73
    ancy
    -0.70
     reven
    -0.67
     backups
    -0.66
    alties
    -0.66
    phies
    -0.65
    ainer
    -0.65
    POSITIVE LOGITS
     chem
    0.65
    igans
    0.65
    gnu
    0.64
     nurture
    0.64
     satur
    0.63
    ominated
    0.60
     Sag
    0.60
     Monstrous
    0.60
     Cellular
    0.59
     Prairie
    0.59
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.