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

    Neuronpedia

    INDEX
    Explanations

    Netflix

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     rings
    -0.07
     preorder
    -0.06
     пользователя
    -0.06
    ़र
    -0.06
     dgv
    -0.06
     disse
    -0.06
     acompan
    -0.06
     narr
    -0.06
    Lord
    -0.06
     [\
    -0.06
    POSITIVE LOGITS
     Netflix
    0.32
    Netflix
    0.27
    flix
    0.14
    .netflix
    0.10
     Spotify
    0.09
    .spotify
    0.08
    otify
    0.08
     sağlamak
    0.07
     Pinterest
    0.07
    spotify
    0.07
    Act Density 0.002%

    No Known Activations