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

    Neuronpedia

    INDEX
    Explanations

    commas

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Moscow
    -0.06
    ████
    -0.06
     są
    -0.06
     \%
    -0.06
     Graves
    -0.06
    `](
    -0.06
     classrooms
    -0.06
    758
    -0.06
     Silver
    -0.06
    ानद
    -0.06
    POSITIVE LOGITS
     pcl
    0.07
    :[[
    0.07
     tkinter
    0.06
     fancy
    0.06
    ův
    0.06
    /train
    0.06
     thing
    0.06
    관리
    0.06
     khác
    0.06
     druh
    0.06
    Act Density 0.043%

    No Known Activations