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

    Neuronpedia

    INDEX
    Explanations

    web page navigation code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     offspring
    -0.09
     teeth
    -0.08
    割
    -0.08
     laugh
    -0.08
     excerpt
    -0.08
     slaughter
    -0.08
     lachen
    -0.08
     laughs
    -0.08
    笑
    -0.08
    ုတ္
    -0.07
    POSITIVE LOGITS
     URLs
    0.13
     방문
    0.13
    网址
    0.13
    URLs
    0.13
     urls
    0.12
     Visiting
    0.12
     visiting
    0.12
    Urls
    0.12
    (url
    0.12
    urls
    0.12
    Act Density 0.008%

    No Known Activations