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

    Neuronpedia

    INDEX
    Explanations

    high

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    办理
    -0.08
     twin
    -0.08
    被执行
    -0.07
    Principal
    -0.07
     Millenn
    -0.07
    .mail
    -0.07
    แก
    -0.07
     khuyến
    -0.07
     anew
    -0.07
     dedicate
    -0.07
    POSITIVE LOGITS
    FileSystem
    0.07
    事が
    0.07
    (stats
    0.07
    .getRow
    0.06
    .bool
    0.06
    КА
    0.06
     seconds
    0.06
    ➴
    0.06
     Hair
    0.06
    者が
    0.06
    Act Density 0.025%

    No Known Activations