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

    Neuronpedia

    INDEX
    Explanations

    Abstract ideas

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     праці
    -0.07
     recognizer
    -0.07
     آور
    -0.06
     ринку
    -0.06
    RU
    -0.06
    حدث
    -0.06
     сопров
    -0.06
    Sit
    -0.06
     meny
    -0.06
    The
    -0.06
    POSITIVE LOGITS
    (Tree
    0.06
    ecret
    0.06
    ,True
    0.06
     Bott
    0.06
     -----
    0.06
    =UTF
    0.06
    ateurs
    0.06
     Bone
    0.06
     Hải
    0.06
    /Web
    0.06
    Act Density 0.133%

    No Known Activations