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

    Neuronpedia

    INDEX
    Explanations

    fact

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _JOB
    -0.06
     economist
    -0.06
    (conf
    -0.06
     classical
    -0.06
     advancement
    -0.06
    (hwnd
    -0.06
    ليف
    -0.06
    もしれない
    -0.06
     minut
    -0.06
     تفس
    -0.06
    POSITIVE LOGITS
     mayoría
    0.07
     Simply
    0.06
    athi
    0.06
     Chi
    0.06
     형
    0.06
    yne
    0.06
    찌
    0.06
     stagn
    0.06
     �
    0.05
     Polar
    0.05
    Act Density 0.002%

    No Known Activations