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

    Neuronpedia

    INDEX
    Explanations

    computer code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    �
    -0.08
    @show
    -0.08
    (saved
    -0.07
    []{
    -0.07
    _province
    -0.07
     ViewData
    -0.07
    _Osc
    -0.06
     diseñ
    -0.06
    {-
    -0.06
    ='+
    -0.06
    POSITIVE LOGITS
    lesson
    0.08
    ialis
    0.07
    tw
    0.07
    信心
    0.07
     HER
    0.07
    дает
    0.07
     Yuri
    0.07
     utils
    0.06
    חלל
    0.06
    جر
    0.06
    Act Density 0.022%

    No Known Activations