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

    Neuronpedia

    INDEX
    Explanations

    TH

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Playback
    -0.07
    装修
    -0.07
    _Items
    -0.07
     dõ
    -0.07
    <button
    -0.07
     protester
    -0.07
    (tx
    -0.07
     rotational
    -0.07
    (cache
    -0.07
     Buffer
    -0.07
    POSITIVE LOGITS
     cấp
    0.07
    ﹷ
    0.07
    布鲁
    0.07
    谫
    0.07
     Ils
    0.07
    .And
    0.07
     pricey
    0.07
    统计局
    0.07
    ♊
    0.07
    之一
    0.07
    Act Density 0.040%

    No Known Activations