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

    Neuronpedia

    INDEX
    Explanations

    legal or scientific documents

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    小鸟
    -0.07
    Accessory
    -0.07
    ורחים
    -0.07
    绿茶
    -0.07
     tươi
    -0.07
     submissions
    -0.07
    臭
    -0.07
     stolen
    -0.07
     Cavaliers
    -0.07
    [thread
    -0.06
    POSITIVE LOGITS
    Environmental
    0.07
    DEFINE
    0.07
    cona
    0.07
    פרק
    0.07
    นำไป
    0.07
     ',',
    0.07
    нской
    0.07
     GOD
    0.07
    gap
    0.07
    臬
    0.07
    Act Density 0.183%

    No Known Activations