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

    Neuronpedia

    INDEX
    Explanations

    default

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     mornings
    -0.08
    ूप
    -0.08
     सुबह
    -0.07
     academically
    -0.07
    .Matrix
    -0.07
     breakfasts
    -0.07
    活
    -0.07
     natürliche
    -0.07
     Coy
    -0.07
     प्राकृतिक
    -0.07
    POSITIVE LOGITS
    _ROM
    0.09
     нужен
    0.09
     menuju
    0.09
     өчен
    0.08
     товара
    0.08
     sams
    0.07
     нужна
    0.07
    ��
    0.07
     Kas
    0.07
     обратиться
    0.07
    Act Density 0.001%

    No Known Activations