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

    Neuronpedia

    INDEX
    Explanations

    least

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    =top
    -0.07
    WINDOW
    -0.07
    -Day
    -0.07
    .hy
    -0.07
     rainy
    -0.07
     thicker
    -0.06
    효
    -0.06
     downhill
    -0.06
     aluminum
    -0.06
    衡
    -0.06
    POSITIVE LOGITS
    研究
    0.07
     MouseEvent
    0.07
    ASP
    0.07
    m
    0.06
    _ENTITY
    0.06
     InvalidArgumentException
    0.06
    Further
    0.06
     закон
    0.06
     also
    0.06
     compliance
    0.06
    Act Density 0.002%

    No Known Activations