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

    Neuronpedia

    INDEX
    Explanations

    prices

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    年来
    -0.07
    ่อง
    -0.07
    袁
    -0.07
    [str
    -0.06
    湘
    -0.06
    沈
    -0.06
    📧
    -0.06
    ingham
    -0.06
     ws
    -0.06
    (global
    -0.06
    POSITIVE LOGITS
    otation
    0.07
     grammar
    0.07
     loops
    0.07
    芴
    0.07
    _Height
    0.07
    売る
    0.07
    -foot
    0.07
    ']")↵
    0.06
    shopping
    0.06
    贵宾
    0.06
    Act Density 0.021%

    No Known Activations