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

    Neuronpedia

    INDEX
    Explanations

    software engineering principles

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    软雅黑
    -0.07
     source
    -0.06
    �权
    -0.06
     Shar
    -0.06
     شرکت
    -0.06
     removeFrom
    -0.06
     Courtesy
    -0.06
    目前
    -0.05
    UPI
    -0.05
    /stat
    -0.05
    POSITIVE LOGITS
    |()↵
    0.07
     caution
    0.06
     slew
    0.06
     asiat
    0.06
    ility
    0.06
     angry
    0.06
    .best
    0.06
    Χ
    0.06
     render
    0.06
     जव
    0.06
    Act Density 0.023%

    No Known Activations