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

    Neuronpedia

    INDEX
    Explanations

    still

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Incorporated
    -0.08
     dụ
    -0.07
    婚姻
    -0.07
     içerisinde
    -0.07
    难度
    -0.07
    海量
    -0.07
     عدد
    -0.07
    _RUN
    -0.07
    Video
    -0.07
    (convert
    -0.07
    POSITIVE LOGITS
     satin
    0.07
    桲
    0.07
     SEN
    0.07
    blah
    0.06
    DRAM
    0.06
    (TABLE
    0.06
     getVersion
    0.06
    泖
    0.06
    剧中
    0.06
    alers
    0.06
    Act Density 0.008%

    No Known Activations