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

    Neuronpedia

    INDEX
    Explanations

    regulations and quality control

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    充滿
    -0.07
    獲
    -0.07
    我们都
    -0.07
    umann
    -0.07
    ลาย
    -0.07
    [loc
    -0.06
     exp
    -0.06
    (fl
    -0.06
    なければ
    -0.06
    (tbl
    -0.06
    POSITIVE LOGITS
     batch
    0.07
    总共
    0.07
    sprite
    0.07
    future
    0.07
    squeeze
    0.07
    nerRadius
    0.07
    Backend
    0.07
    :left
    0.06
    /on
    0.06
    ).</
    0.06
    Act Density 0.055%

    No Known Activations