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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    noise
    -0.07
    oled
    -0.07
    -rad
    -0.07
    ]<
    -0.07
    coded
    -0.07
    estado
    -0.07
    '](
    -0.07
    ]>↵
    -0.07
    (admin
    -0.06
    generic
    -0.06
    POSITIVE LOGITS
    �
    0.07
     혹은
    0.07
    议
    0.07
     biến
    0.06
    _GET
    0.06
     hồi
    0.06
     취
    0.06
    (Transform
    0.06
    慮
    0.06
     각종
    0.06
    Act Density 0.011%

    No Known Activations