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

    Neuronpedia

    INDEX
    Explanations

    in

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Ford
    -0.06
     Benedict
    -0.06
    .ReadUInt
    -0.06
     moss
    -0.06
    eway
    -0.06
    uniacid
    -0.06
     care
    -0.06
    maze
    -0.06
     methane
    -0.06
    Sans
    -0.06
    POSITIVE LOGITS
    instagram
    0.07
    48
    0.06
    これ
    0.06
    �
    0.06
    番組
    0.06
    変
    0.06
    _deposit
    0.06
     bilgisayar
    0.06
    subcategory
    0.06
     世界
    0.06
    Act Density 0.071%

    No Known Activations