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

    Neuronpedia

    INDEX
    Explanations

    is

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .logo
    -0.07
    @Controller
    -0.07
    獲
    -0.07
     seulement
    -0.07
    ٹ
    -0.06
    restricted
    -0.06
    ‹
    -0.06
     الديمقراطية
    -0.06
    ok
    -0.06
    在北京
    -0.06
    POSITIVE LOGITS
    notification
    0.07
    collision
    0.07
     onError
    0.07
    Verdana
    0.07
    andr
    0.07
     damping
    0.07
    مواقف
    0.07
    伤亡
    0.07
    	URL
    0.07
    巡查
    0.07
    Act Density 0.000%

    No Known Activations