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

    Neuronpedia

    INDEX
    Explanations

    product

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    푸
    -0.07
     descending
    -0.07
    硬盘
    -0.07
    straction
    -0.07
    <Key
    -0.06
     dop
    -0.06
     posición
    -0.06
    ﰰ
    -0.06
    (INFO
    -0.06
     Icelandic
    -0.06
    POSITIVE LOGITS
     е
    0.08
    /blob
    0.08
    ⺠
    0.08
    _WORLD
    0.07
     sale
    0.07
    .feed
    0.07
    Qed
    0.07
    话剧
    0.07
     whales
    0.06
    ほか
    0.06
    Act Density 0.003%

    No Known Activations