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

    Neuronpedia

    INDEX
    Explanations

    Class descriptions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ♀
    -0.07
    _students
    -0.06
    :");↵
    -0.06
     spawns
    -0.06
     MSE
    -0.06
    796
    -0.06
     слив
    -0.06
    _sal
    -0.06
    ProductName
    -0.06
    depends
    -0.06
    POSITIVE LOGITS
     долж
    0.07
     종
    0.07
    باز
    0.06
     WK
    0.06
    >Z
    0.06
    .et
    0.06
    เฉล
    0.06
    ────
    0.06
    níku
    0.06
    ardır
    0.06
    Act Density 0.038%

    No Known Activations