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

    Neuronpedia

    INDEX
    Explanations

    quotation mark

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     سفر
    -0.07
    _aug
    -0.06
     TJ
    -0.06
    -im
    -0.06
    ">'.$
    -0.06
     agencies
    -0.06
    서관
    -0.06
    (force
    -0.06
    '};↵
    -0.06
    홍
    -0.06
    POSITIVE LOGITS
    IDDLE
    0.07
     ears
    0.06
     rookie
    0.06
     previous
    0.06
    )dealloc
    0.06
    ुछ
    0.06
    HELP
    0.06
    toMatchSnapshot
    0.06
     compte
    0.06
     erotica
    0.06
    Act Density 0.015%

    No Known Activations