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

    Neuronpedia

    INDEX
    Explanations

    link

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    퀀
    -0.07
     منه
    -0.07
     البرلم
    -0.07
    _replace
    -0.07
    اخبار
    -0.07
     LINUX
    -0.07
     interracial
    -0.07
     merupakan
    -0.06
     Tiểu
    -0.06
     uğ
    -0.06
    POSITIVE LOGITS
    透明
    0.08
     know
    0.08
    داء
    0.07
     Ease
    0.07
    ホ
    0.07
     coordinated
    0.07
    training
    0.07
    Computed
    0.07
    tero
    0.06
    覆盖
    0.06
    Act Density 0.008%

    No Known Activations