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

    Neuronpedia

    INDEX
    Explanations

    code and system terms

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    高中
    -0.07
    网民
    -0.07
     grazing
    -0.07
     carbs
    -0.07
    了不少
    -0.07
     Đoàn
    -0.07
    弦
    -0.07
    เฉพาะ
    -0.07
     Dire
    -0.07
     Frem
    -0.07
    POSITIVE LOGITS
    masked
    0.09
    -mount
    0.09
    𝚖
    0.08
     пут
    0.07
    موت
    0.07
     ashes
    0.07
    -bl
    0.07
     glob
    0.07
    TestFixture
    0.07
    龠
    0.07
    Act Density 0.285%

    No Known Activations