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

    Neuronpedia

    INDEX
    Explanations

    for

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _SPI
    -0.07
     Aunt
    -0.07
     öğ
    -0.06
     ART
    -0.06
    props
    -0.06
     Lu
    -0.06
     ihm
    -0.06
    同学
    -0.06
    ($
    -0.06
     gearbox
    -0.06
    POSITIVE LOGITS
    utorial
    0.07
    維
    0.06
     bev
    0.06
    PreferredGap
    0.06
     Loud
    0.06
     oči
    0.06
    surname
    0.06
    监听页面
    0.06
    Lazy
    0.06
     pkt
    0.06
    Act Density 0.001%

    No Known Activations