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

    Neuronpedia

    INDEX
    Explanations

    =

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .bindingNavigator
    -0.07
    yps
    -0.07
    etermine
    -0.07
    打印
    -0.07
    iscing
    -0.07
    (Size
    -0.06
     ding
    -0.06
    同比下降
    -0.06
     pj
    -0.06
    Debe
    -0.06
    POSITIVE LOGITS
     FRAME
    0.09
     коллектив
    0.07
     الاخ
    0.07
     battling
    0.07
     swipe
    0.07
     ад
    0.07
    ipeline
    0.07
     الا
    0.06
    .getAmount
    0.06
     Plate
    0.06
    Act Density 0.032%

    No Known Activations