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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    pite
    -0.83
    Ire
    -0.73
    rarily
    -0.72
    Weiss
    -0.71
    SourceFile
    -0.69
    utsch
    -0.68
    EXT
    -0.67
    оÐ
    -0.66
    ascus
    -0.65
    MpServer
    -0.65
    POSITIVE LOGITS
    enegger
    0.71
     Bri
    0.63
     loop
    0.61
     PayPal
    0.60
     cred
    0.60
     uphill
    0.59
     Prevent
    0.59
     overriding
    0.59
    aday
    0.58
     pc
    0.57
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.