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

    Neuronpedia

    INDEX
    Explanations

    ably

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     середови
    -0.06
    يلا
    -0.06
     zs
    -0.06
    ]),
    -0.06
    たちは
    -0.05
     nosotros
    -0.05
     RectTransform
    -0.05
     использовать
    -0.05
    ителей
    -0.05
     Euro
    -0.05
    POSITIVE LOGITS
     adequ
    0.08
     preferably
    0.07
    ¼
    0.07
    اسي
    0.07
    458
    0.07
    责任
    0.07
     
    0.07
     cane
    0.07
     predominantly
    0.07
    anning
    0.06
    Act Density 0.005%

    No Known Activations