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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    .
    0.73
    ique
    0.71
    $)
    0.71
    .$
    0.70
     Heritage
    0.70
     will
    0.66
     Williams
    0.66
     Salamanca
    0.66
    }{$
    0.65
    |
    0.65
    POSITIVE LOGITS
    which
    0.84
    roles
    0.82
     mandib
    0.80
    specifically
    0.78
     ዓይነ
    0.76
     которые
    0.75
     이러한
    0.75
    Loksatta
    0.75
    ўцаў
    0.75
     orchestras
    0.75
    Act Density 0.797%

    No Known Activations