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

    Neuronpedia

    INDEX
    Explanations

    numerical values and special characters, particularly in the context of academic citations or references

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

    Numbers in parentheses or brackets

    np_acts-logits-general · gemini-2.0-flash

    citations and academic papers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    kannya
    -0.60
     storici
    -0.59
    ghts
    -0.57
    BuilderFactory
    -0.56
     aikaa
    -0.55
     résister
    -0.55
    Démographie
    -0.52
    autoreleasepool
    -0.52
     habituales
    -0.50
    HtmlAttribute
    -0.50
    POSITIVE LOGITS
     дописавши
    0.82
    ⓧ
    0.54
     jScrollPane
    0.52
     utafitiHapana
    0.51
    AUTHOR
    0.48
    )|^{
    0.48
    )}^{
    0.48
    }\|
    0.47
    UpInside
    0.47
     preprint
    0.47
    Act Density 0.041%

    No Known Activations