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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     propagating
    0.78
     figuratively
    0.78
     Scrooge
    0.70
     которыми
    0.68
     TensorFlow
    0.68
     paralle
    0.67
    मधील
    0.67
     gratifying
    0.67
     Josie
    0.67
    каў
    0.67
    POSITIVE LOGITS
    Lä
    0.74
    A
    0.73
    B
    0.70
     matchs
    0.66
    Б
    0.66
    aient
    0.65
    чак
    0.64
    ït
    0.63
    Кла
    0.63
     carénés
    0.62
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.