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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     služby
    0.95
     créditos
    0.92
     adaptador
    0.90
    $)$.
    0.85
     vitaminas
    0.84
     melhores
    0.84
     famílias
    0.84
     policías
    0.84
     doença
    0.83
     doenças
    0.83
    POSITIVE LOGITS
    H
    0.86
    EL
    0.80
    DO
    0.77
    B
    0.77
    Z
    0.77
    T
    0.76
    Due
    0.76
    R
    0.75
    W
    0.74
    J
    0.72
    Act Density 0.003%

    No Known Activations