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

    Neuronpedia

    INDEX
    Explanations

    references to specific scientific studies or authors in the text

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

    References/citations within brackets

    np_acts-logits-general · gemini-2.0-flash

    citation authors like Wang, Yang

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    EndGlobal
    -0.57
     ब्रेकडाउन
    -0.57
    withIdentifier
    -0.56
    sizeCache
    -0.54
    外部リンク
    -0.54
    脚注の使い方
    -0.53
    請繼續往下閱讀
    -0.52
    enity
    -0.51
     lenker
    -0.51
    didSet
    -0.50
    POSITIVE LOGITS
    //
    0.41
    recent
    0.40
    Recent
    0.37
    ThroughAttribute
    0.37
     recent
    0.36
    reviewed
    0.36
    studies
    0.36
     Zhou
    0.36
     Zhang
    0.36
     authors
    0.36
    Act Density 0.550%

    No Known Activations