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

    Neuronpedia

    INDEX
    Explanations

    px

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Mil
    -0.07
    (right
    -0.07
    僚
    -0.06
    ﭺ
    -0.06
    恰好
    -0.06
    bour
    -0.06
    砣
    -0.06
     Karma
    -0.06
     diffusion
    -0.06
    棱
    -0.06
    POSITIVE LOGITS
    提取
    0.08
    겆
    0.07
    老鼠
    0.07
    表彰
    0.07
    �
    0.07
    演唱
    0.06
     قائ
    0.06
    退出
    0.06
    Ǒ
    0.06
    _GENER
    0.06
    Act Density 0.008%

    No Known Activations