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

    Neuronpedia

    INDEX
    Explanations

    is

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Adventure
    -0.06
    创投
    -0.06
     Institut
    -0.06
    救
    -0.06
    �
    -0.06
    ẩn
    -0.06
    源于
    -0.06
    蛰
    -0.06
    隧
    -0.06
     born
    -0.06
    POSITIVE LOGITS
    -widgets
    0.07
    digit
    0.07
    _Page
    0.07
    对其进行
    0.07
    <WebElement
    0.07
    arsity
    0.07
    嫂
    0.07
    .Other
    0.07
     Obl
    0.07
    VERRIDE
    0.06
    Act Density 0.014%

    No Known Activations