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

    Neuronpedia

    INDEX
    Explanations

    Questions and suggestions

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    艾滋病
    -0.08
    .getParameter
    -0.08
    HomeAsUpEnabled
    -0.07
    气候
    -0.07
    不断地
    -0.07
    .djangoproject
    -0.07
     vibrant
    -0.07
     الجن
    -0.07
    医科大学
    -0.07
    ']
    -0.07
    POSITIVE LOGITS
    套
    0.08
    hp
    0.07
    嫱
    0.07
    ocolate
    0.07
    妹
    0.07
     comfy
    0.07
    随手
    0.07
    Even
    0.07
    remarks
    0.07
    memory
    0.06
    Act Density 0.018%

    No Known Activations