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

    Neuronpedia

    INDEX
    Explanations

    Courtesy

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     getColumn
    -0.08
     incap
    -0.06
    تكو
    -0.06
    umn
    -0.06
    oras
    -0.06
     getColor
    -0.06
    “What
    -0.06
    oor
    -0.06
    _turn
    -0.06
     snowy
    -0.06
    POSITIVE LOGITS
     бренд
    0.07
    _]
    0.06
     underside
    0.06
     equipe
    0.06
     онлайн
    0.06
    하자
    0.06
    RK
    0.06
    עצ
    0.06
    /////
    0.06
    一则
    0.06
    Act Density 0.002%

    No Known Activations