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

    Neuronpedia

    INDEX
    Explanations

    measurement

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    岁以下
    -0.08
    飒
    -0.07
    漾
    -0.07
    低价
    -0.07
    下げ
    -0.07
    ㇾ
    -0.07
    óg
    -0.07
     Luz
    -0.07
    %%%%%%%%
    -0.07
    惠
    -0.07
    POSITIVE LOGITS
    strpos
    0.08
    _VECTOR
    0.07
    Whenever
    0.07
    (comb
    0.07
    的比赛
    0.07
    (media
    0.07
    碰
    0.07
    arked
    0.07
    פק
    0.07
    ctica
    0.07
    Act Density 0.055%

    No Known Activations