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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     Lung
    -0.72
     Bowen
    -0.66
     Madness
    -0.66
     Lur
    -0.65
     (%
    -0.64
     Guam
    -0.63
     Dempsey
    -0.60
    ``
    -0.60
    ([
    -0.60
    Mand
    -0.59
    POSITIVE LOGITS
     season
    0.89
    utenberg
    0.87
    arte
    0.77
    ounter
    0.75
     Cosponsors
    0.74
    intendent
    0.71
    DragonMagazine
    0.69
    endar
    0.68
     conductor
    0.66
    hani
    0.65
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.