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

    Neuronpedia

    INDEX
    Explanations

    updates or human beings

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    يكب
    -0.57
    ázaro
    -0.54
    scha
    -0.48
    nati
    -0.47
    lacoste
    -0.47
     BufferedImage
    -0.46
     étend
    -0.46
     Plans
    -0.46
    amaha
    -0.46
    sste
    -0.46
    POSITIVE LOGITS
     estekak
    0.79
     onOptions
    0.66
    出版年
    0.63
     дописавши
    0.63
    AndEndTag
    0.62
    참고
    0.62
     Infórmanos
    0.59
    ValueStyle
    0.58
    GEBURTS
    0.57
    hatsu
    0.56
    Act Density 1.746%

    No Known Activations