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

    Neuronpedia

    INDEX
    Explanations

    research studies

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    []}
    -0.07
    .Where
    -0.07
    Magic
    -0.07
    iya
    -0.06
    COMMAND
    -0.06
    _POS
    -0.06
     dorm
    -0.06
    とも
    -0.06
     bốn
    -0.06
    DEV
    -0.06
    POSITIVE LOGITS
    ματα
    0.07
    (render
    0.06
    __$
    0.06
     Απο
    0.06
    Percent
    0.06
     الاع
    0.06
     مقاله
    0.06
     Gle
    0.06
     obou
    0.06
    _third
    0.06
    Act Density 0.050%

    No Known Activations