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

    Neuronpedia

    INDEX
    Explanations

    error

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     (),
    -0.08
    (square
    -0.08
    ב
    -0.06
     comme
    -0.06
     she
    -0.06
     Zot
    -0.06
     ب
    -0.06
     airl
    -0.06
     dug
    -0.06
    ５
    -0.06
    POSITIVE LOGITS
    userInfo
    0.07
    :title
    0.07
    .channels
    0.07
    asurable
    0.07
    POSITION
    0.07
    ☘
    0.07
    获胜
    0.07
    _registration
    0.06
    مشاكل
    0.06
    优惠
    0.06
    Act Density 0.019%

    No Known Activations