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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    eware
    -0.69
     Forbidden
    -0.67
    closed
    -0.66
    wl
    -0.64
     latitude
    -0.61
     Butterfly
    -0.61
     Breach
    -0.60
     embargo
    -0.59
    mys
    -0.59
    onday
    -0.58
    POSITIVE LOGITS
    doms
    0.75
    gang
    0.73
    itaire
    0.72
    cules
    0.71
    trak
    0.68
     Cree
    0.67
    Hero
    0.66
    tags
    0.65
    geant
    0.65
    ida
    0.64
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.