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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     ÂŃ
    -0.75
     Devils
    -0.67
     Coyotes
    -0.67
     Filipino
    -0.66
     Panthers
    -0.66
     Rivera
    -0.64
     Marin
    -0.64
     Laurel
    -0.63
     Instagram
    -0.63
     Angola
    -0.62
    POSITIVE LOGITS
    APD
    0.80
    asca
    0.72
     competent
    0.72
    ħĭ
    0.70
    hire
    0.70
    Default
    0.68
     headache
    0.68
    hib
    0.68
    consumer
    0.68
    cook
    0.67
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.