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

    Neuronpedia

    INDEX
    Explanations

    sharing links and URLs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     limitation
    0.45
     delays
    0.44
    Fur
    0.42
    Limitations
    0.42
     limitations
    0.41
     trache
    0.40
     shoe
    0.39
     fur
    0.39
    стей
    0.38
     grace
    0.38
    POSITIVE LOGITS
    share
    0.56
     Share
    0.51
    gmail
    0.48
    shareButton
    0.47
     xhr
    0.47
     SHARE
    0.45
    stdio
    0.43
    Share
    0.43
    chrome
    0.42
    sidebar
    0.42
    Act Density 0.003%

    No Known Activations