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

    Neuronpedia

    INDEX
    Explanations

    Code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Needed
    -0.06
    Typed
    -0.06
     Sociology
    -0.06
     fitted
    -0.06
    麗
    -0.06
    Assignment
    -0.06
    _polygon
    -0.06
     sociology
    -0.06
     bỏ
    -0.06
    -side
    -0.06
    POSITIVE LOGITS
    优势
    0.06
    /weather
    0.06
    createTime
    0.06
     関
    0.06
     relinqu
    0.06
     Iron
    0.06
    ̣
    0.06
     "");↵
    0.06
     アイ
    0.06
    _Renderer
    0.06
    Act Density 0.114%

    No Known Activations