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

    Neuronpedia

    INDEX
    Explanations

    notch

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    üst
    -0.08
    писыва
    -0.07
    _CITY
    -0.07
    ليك
    -0.07
    board
    -0.07
    픠
    -0.07
    ServletRequest
    -0.07
     Plum
    -0.07
    饲
    -0.07
    flowers
    -0.07
    POSITIVE LOGITS
     Кар
    0.07
     فال
    0.06
     loot
    0.06
     ERA
    0.06
    /Auth
    0.06
     `${
    0.06
    手機
    0.06
    醫療
    0.06
     למשל
    0.06
     различных
    0.06
    Act Density 0.002%

    No Known Activations