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

    Neuronpedia

    INDEX
    Explanations

    Tasks and chores

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    中国人
    -0.07
    救
    -0.07
    =False
    -0.07
    Consumer
    -0.07
     sulfate
    -0.07
     fuel
    -0.06
    不能
    -0.06
    兵
    -0.06
    OA
    -0.06
     soldiers
    -0.06
    POSITIVE LOGITS
     работает
    0.07
    🍰
    0.07
     Skyl
    0.07
     II
    0.07
    <Game
    0.06
    谁知道
    0.06
    Actualizar
    0.06
    苉
    0.06
    Flight
    0.06
    堞
    0.06
    Act Density 0.107%

    No Known Activations