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

    Neuronpedia

    INDEX
    Explanations

    game rules

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     suchen
    -0.07
    セ
    -0.06
    小时
    -0.06
     Tier
    -0.06
    components
    -0.06
    eted
    -0.06
    prar
    -0.06
    وب
    -0.06
    ショ
    -0.06
    té
    -0.05
    POSITIVE LOGITS
     bgColor
    0.07
    ==-
    0.07
    avigate
    0.06
    態
    0.06
     republican
    0.06
     getC
    0.06
     FOOD
    0.06
    /ch
    0.06
     pneumonia
    0.06
    Liquid
    0.06
    Act Density 0.019%

    No Known Activations