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

    Neuronpedia

    INDEX
    Explanations

    by

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _cmp
    -0.07
    ⚜
    -0.07
    ᛞ
    -0.06
     sixteen
    -0.06
     knack
    -0.06
     mentioned
    -0.06
     Notification
    -0.06
     Scheduled
    -0.06
    န
    -0.06
    maf
    -0.06
    POSITIVE LOGITS
    拥堵
    0.08
    乐视
    0.07
    oblins
    0.07
     Maryland
    0.07
    -Cola
    0.07
    运行
    0.07
    庞大
    0.07
    越大
    0.07
    (parse
    0.07
    戏曲
    0.07
    Act Density 0.003%

    No Known Activations