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

    Neuronpedia

    INDEX
    Explanations

    ;

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Marlins
    -0.07
    ILON
    -0.07
    para
    -0.07
    嶍
    -0.07
    쩝
    -0.07
    在网上
    -0.06
     Veteran
    -0.06
    <App
    -0.06
    蕗
    -0.06
    arden
    -0.06
    POSITIVE LOGITS
    _frac
    0.09
    游戏当中
    0.08
     Sự
    0.07
     personality
    0.07
     السعود
    0.07
     películ
    0.07
    .put
    0.07
     prejudices
    0.07
     ASCII
    0.06
    スポーツ
    0.06
    Act Density 0.012%

    No Known Activations