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

    Neuronpedia

    INDEX
    Explanations

    caution about data changes

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    רפואה
    -0.07
    婿
    -0.07
     Leon
    -0.07
     enquiry
    -0.07
    中の
    -0.07
    我們
    -0.07
     Kong
    -0.07
     의사
    -0.06
    LR
    -0.06
    lesen
    -0.06
    POSITIVE LOGITS
    ersions
    0.07
    <Scalar
    0.07
    .localtime
    0.07
    变革
    0.07
     ($("#
    0.07
    鲇
    0.06
    hiba
    0.06
    ҽ
    0.06
    光环
    0.06
    го
    0.06
    Act Density 0.032%

    No Known Activations