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

    Neuronpedia

    INDEX
    Explanations

    at

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ↵↵↵
    -0.07
     prosperity
    -0.07
     explosion
    -0.07
     미
    -0.07
    _helper
    -0.07
    _FMT
    -0.07
    흠
    -0.07
    繁荣
    -0.07
     인정
    -0.07
     St
    -0.07
    POSITIVE LOGITS
    鹔
    0.07
    CLU
    0.07
    갯
    0.07
    .FileOutputStream
    0.07
    ammad
    0.07
    BarController
    0.07
    궈
    0.06
    ﰘ
    0.06
    濩
    0.06
    再也不
    0.06
    Act Density 0.003%

    No Known Activations