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

    Neuronpedia

    INDEX
    Explanations

    sections and headings related to references, notes, and acknowledgments in documents

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

    Text preceding "References", "Description", or "Captions"

    np_acts-logits-general · gemini-2.0-flash

    section headings and references

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    =',
    -0.49
    <%=
    -0.48
    Gweler
    -0.46
    ItemBackground
    -0.46
    =",
    -0.46
     उसे
    -0.46
     hadiah
    -0.45
    =#{
    -0.45
    ednesdays
    -0.45
    antMatchers
    -0.45
    POSITIVE LOGITS
     AssemblyCulture
    0.94
    tvguidetime
    0.81
    :✨
    0.79
    RegressionTest
    0.75
     متعلقه
    0.74
    ंदीखरीदारी
    0.73
    Przypisy
    0.73
    parsedMessage
    0.72
    RenderAtEndOf
    0.70
    MessageTagHelper
    0.69
    Act Density 0.481%

    No Known Activations