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

    Neuronpedia

    INDEX
    Explanations

    2

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    æĪIJ绩
    -0.31
     performance
    -0.27
    绩æķĪ
    -0.27
     commend
    -0.27
    tt
    -0.26
     surpassed
    -0.26
    -meta
    -0.25
    åŃ¦ä¹łæĪIJ绩
    -0.25
     surpass
    -0.25
    è¶ħ
    -0.25
    POSITIVE LOGITS
    é±¼
    0.27
     //</
    0.26
    ergy
    0.26
    æĮ¤åİĭ
    0.25
    é©»
    0.25
    ActionButton
    0.25
    ä¸Ģ件
    0.25
    aghan
    0.25
    éĺ´è°ĭ
    0.24
    幸ç¦ı
    0.24
    Act Density 1.111%

    No Known Activations