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

    Neuronpedia

    INDEX
    Explanations

    period

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    met
    -0.07
    svg
    -0.07
    纳
    -0.07
     cough
    -0.06
    spar
    -0.06
    .median
    -0.06
     baise
    -0.06
    涉
    -0.06
    ere
    -0.06
    📕
    -0.06
    POSITIVE LOGITS
    -thumb
    0.07
    important
    0.07
    TestData
    0.07
     Bearings
    0.07
    南京
    0.07
    注意事项
    0.07
    eña
    0.07
    .UInt
    0.07
    inds
    0.07
    	UInt
    0.07
    Act Density 0.002%

    No Known Activations