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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    愃
    -0.07
    _IRQHandler
    -0.07
    犴
    -0.07
    痉
    -0.06
     `%
    -0.06
    跱
    -0.06
     Мос
    -0.06
     burgeoning
    -0.06
    xor
    -0.06
    node
    -0.06
    POSITIVE LOGITS
    國家
    0.07
    _logger
    0.07
     hubby
    0.07
     hypoc
    0.07
     cables
    0.07
    (lower
    0.07
    _emit
    0.07
     אחרונים
    0.07
     ymax
    0.06
    🔲
    0.06
    Act Density 0.003%

    No Known Activations