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

    Neuronpedia

    INDEX
    Explanations

    code and natural language

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     nevy
    -0.08
     diversas
    -0.07
    agonal
    -0.07
    属性
    -0.07
     ho
    -0.07
     optics
    -0.07
     thức
    -0.06
     voiced
    -0.06
     covariance
    -0.06
    ovala
    -0.06
    POSITIVE LOGITS
     чай
    0.07
    енню
    0.06
    Except
    0.06
    (Stack
    0.06
    .mark
    0.06
     円
    0.06
     TBranch
    0.06
    ้เป
    0.06
    .package
    0.06
    findFirst
    0.06
    Act Density 0.323%

    No Known Activations