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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     atrocities
    0.98
     insurrection
    0.97
     लड़का
    0.97
     abolish
    0.96
    κρα
    0.94
    来实现
    0.93
     oppression
    0.92
     ಕ್ಷೇತ್ರದ
    0.91
     equivariant
    0.91
     sogenannte
    0.89
    POSITIVE LOGITS
    a
    0.95
     எண்ணெய்
    0.80
    alty
    0.75
    ați
    0.74
    neat
    0.73
    divider
    0.72
    ellos
    0.71
    elti
    0.70
    koľ
    0.70
     deft
    0.69
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.