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

    Neuronpedia

    INDEX
    Explanations

    >

    np_max-act · gemini-2.0-flash

    The neuron fires on HTML markup tags, especially the opening `<head>` and `<style>` elements.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     ImmutableList
    -0.07
     内
    -0.06
    hb
    -0.06
    PagerAdapter
    -0.06
    Fine
    -0.06
    講
    -0.06
    票
    -0.06
     adrenaline
    -0.06
    anvas
    -0.06
    athlon
    -0.06
    POSITIVE LOGITS
     <?
    0.07
     unauthorized
    0.06
    .Api
    0.06
     Druid
    0.06
     dropdown
    0.06
    _support
    0.06
    -led
    0.06
    gets
    0.06
     Stacy
    0.06
     ';↵↵
    0.06
    Act Density 0.004%

    No Known Activations