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

    Neuronpedia

    INDEX
    Explanations

    phrases and words related to summarizing and outlining content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Text preceding summaries or overviews

    np_acts-logits-general · gemini-2.0-flash

    summary and overview of content

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ceptor
    -0.62
    cassert
    -0.57
    حياتها
    -0.55
    GenerationType
    -0.55
     Garvey
    -0.54
     satunya
    -0.53
     pi
    -0.53
    imedia
    -0.52
    endphp
    -0.52
    kannt
    -0.52
    POSITIVE LOGITS
     summaries
    1.03
     summary
    1.01
     summarize
    0.99
     overview
    0.97
     summarise
    0.96
     outline
    0.96
     summarizing
    0.94
    ChildScrollView
    0.91
     Summar
    0.91
    Recap
    0.88
    Act Density 0.244%

    No Known Activations