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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     但是
    0.63
    onaut
    0.61
     一个
    0.58
     定义
    0.57
     应用
    0.57
     然而
    0.56
     Однако
    0.55
     महीना
    0.55
     函数
    0.55
     gejala
    0.55
    POSITIVE LOGITS
     are
    0.47
     येतात
    0.46
     लाभदायक
    0.44
    および
    0.43
    Spirit
    0.43
    зите
    0.43
    既
    0.42
     Spirit
    0.42
    願い
    0.42
     эта
    0.42
    Act Density 0.000%

    No Known Activations