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

    Neuronpedia

    INDEX
    Explanations

    end

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     مدى
    -0.08
    Lar
    -0.08
     tarieven
    -0.08
    esthetic
    -0.08
     lên
    -0.08
     различные
    -0.07
    \Extension
    -0.07
     Enlight
    -0.07
     kê
    -0.07
    extent
    -0.07
    POSITIVE LOGITS
    ด้วย
    0.10
     থেকেই
    0.09
     যে
    0.08
    戴
    0.07
     fresh
    0.07
    Sesion
    0.07
    陈
    0.07
    下来
    0.07
    तः
    0.07
     రోజు
    0.07
    Act Density 0.050%

    No Known Activations