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

    Neuronpedia

    INDEX
    Explanations

    ing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     probs
    -0.07
    动物
    -0.06
    ＿__
    -0.06
    subcategory
    -0.06
    vertise
    -0.06
     ارشد
    -0.06
    /fontawesome
    -0.06
    98
    -0.06
     Bbw
    -0.06
     walls
    -0.06
    POSITIVE LOGITS
    inous
    0.07
     electrical
    0.06
     cigarette
    0.06
     Infinity
    0.06
    기
    0.06
    )*(
    0.06
    ネット
    0.06
     Result
    0.06
    gars
    0.06
    ерт
    0.06
    Act Density 0.015%

    No Known Activations