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

    Neuronpedia

    INDEX
    Explanations

    code snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .System
    -0.06
     Dün
    -0.06
    "The
    -0.06
     forgive
    -0.06
    “How
    -0.06
    كان
    -0.06
    一定
    -0.06
     Dustin
    -0.06
    ippi
    -0.06
     里
    -0.06
    POSITIVE LOGITS
    例
    0.07
     опас
    0.06
     Mỹ
    0.06
    클
    0.06
     právní
    0.06
    .master
    0.06
     뉴
    0.06
     angular
    0.06
    WEBPACK
    0.06
     Scaffold
    0.06
    Act Density 0.023%

    No Known Activations