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

    Neuronpedia

    INDEX
    Explanations

    Abbreviations/initials

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    static
    -0.07
    void
    -0.07
    λικά
    -0.07
    HANDLE
    -0.07
    ___
    -0.06
    stock
    -0.06
    ㅋ
    -0.06
    visible
    -0.06
    もっと
    -0.06
    حي
    -0.06
    POSITIVE LOGITS
     setLoading
    0.08
    >An
    0.06
    conut
    0.06
    ても
    0.06
     attained
    0.06
    ？↵
    0.06
     annoying
    0.06
    ovenant
    0.06
    _configs
    0.06
     район
    0.06
    Act Density 0.065%

    No Known Activations