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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    强烈的
    -0.07
     condition
    -0.07
     arms
    -0.07
    �回
    -0.07
    ريع
    -0.07
     followed
    -0.07
     aux
    -0.07
    oenix
    -0.07
     yield
    -0.06
    原件
    -0.06
    POSITIVE LOGITS
     balcon
    0.07
    تبادل
    0.07
    媖
    0.07
    olf
    0.07
    ставка
    0.07
    褙
    0.07
     SCC
    0.07
    ерж
    0.06
    📶
    0.06
    jah
    0.06
    Act Density 0.028%

    No Known Activations