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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    acly
    -0.76
     onwards
    -0.73
    ysis
    -0.69
     fitt
    -0.69
    aries
    -0.67
     Notting
    -0.67
     Philipp
    -0.66
    ynes
    -0.66
     Cyborg
    -0.66
    ³³
    -0.65
    POSITIVE LOGITS
    oshop
    0.66
     fetal
    0.65
    Frame
    0.64
    CLAIM
    0.63
    gest
    0.63
    istries
    0.61
     prenatal
    0.60
    LAN
    0.59
    zees
    0.59
     payday
    0.59
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.