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

    Neuronpedia

    INDEX
    Explanations

    plasma

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    贩
    -0.08
    而言
    -0.07
     />
↵
    -0.07
    logger
    -0.07
    .spotify
    -0.07
    זן
    -0.06
    墙上
    -0.06
    CNN
    -0.06
    Sound
    -0.06
    학생
    -0.06
    POSITIVE LOGITS
    ,body
    0.07
    顾虑
    0.07
    丝丝
    0.07
    (Unit
    0.07
    开拓
    0.07
     Carbon
    0.07
     중심
    0.06
     preco
    0.06
    -equ
    0.06
    _car
    0.06
    Act Density 0.015%

    No Known Activations