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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    趼
    -1.23
    ガタ
    -1.06
    も見
    -1.06
    气质
    -1.03
    jera
    -1.02
    をよく
    -0.99
    蝼
    -0.97
    khar
    -0.97
    ఝ
    -0.96
    样子
    -0.93
    POSITIVE LOGITS
     are
    0.91
     率
    0.90
     seeming
    0.88
    asList
    0.85
    𝙁
    0.84
    洮
    0.83
     utilizzato
    0.82
     система
    0.82
     mechanism
    0.81
    旅行
    0.79
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.