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

    Neuronpedia

    INDEX
    Explanations

    and

    np_max-act · gemini-2.0-flash

    The neuron fires on floating‐point numeric literals (decimal numbers) in code or comments.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     worksheets
    -0.07
     �
    -0.07
     �
    -0.07
     rpc
    -0.06
     stru
    -0.06
     tro
    -0.06
     brag
    -0.06
     bearer
    -0.06
    ViewPager
    -0.06
     bilin
    -0.06
    POSITIVE LOGITS
     Fuller
    0.07
     intercourse
    0.07
    Profit
    0.07
    oise
    0.07
    相關
    0.06
     Li
    0.06
    歌
    0.06
    .undo
    0.06
    _conversion
    0.06
    steen
    0.06
    Act Density 0.134%

    No Known Activations