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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     probabil
    0.80
     probabilistic
    0.78
     Bernoulli
    0.78
     Sigma
    0.76
     Node
    0.72
    probability
    0.71
    Brush
    0.71
     Brush
    0.71
     Bayesian
    0.70
     probability
    0.70
    POSITIVE LOGITS
    ອາ
    1.01
     considera
    0.88
    <unused1016>
    0.87
    ッキリ
    0.85
     উপযুক্ত
    0.84
     ограни
    0.78
    ອາຫານ
    0.77
    ínsula
    0.76
    weza
    0.76
     existen
    0.74
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.