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

    Neuronpedia

    INDEX
    Explanations

    package

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    рован
    -0.06
    "My
    -0.06
    وى
    -0.06
    xbb
    -0.06
    だった
    -0.06
     SVM
    -0.06
     мо
    -0.06
    กราคม
    -0.06
     Wells
    -0.06
     <!--<
    -0.06
    POSITIVE LOGITS
     Meet
    0.07
    543
    0.07
     UPC
    0.07
     rural
    0.07
    _component
    0.07
    感觉
    0.07
    Linked
    0.07
    assa
    0.07
    checked
    0.07
     segregated
    0.07
    Act Density 0.002%

    No Known Activations