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

    Neuronpedia

    INDEX
    Explanations

    business

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    oe
    -0.10
    ness
    -0.09
    ymy
    -0.09
    ych
    -0.08
    ardware
    -0.08
    issue
    -0.08
    ries
    -0.08
    rospection
    -0.08
    aughters
    -0.08
    ographie
    -0.08
    POSITIVE LOGITS
    办理
    0.14
    线
    0.13
    开展
    0.11
    员
    0.11
    線
    0.10
    流程
    0.10
     tuyến
    0.09
    板
    0.09
    发展的
    0.09
     Daniels
    0.09
    Act Density 0.009%

    No Known Activations