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

    Neuronpedia

    INDEX
    Explanations

    parentheses and mathematical or procedural references in the text

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

    Abbreviations in parentheses

    np_acts-logits-general · gemini-2.0-flash

    acronyms and abbreviations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     समीक्षाओं
    -0.60
    ReusableCell
    -0.59
     فريبيس
    -0.53
     Allen
    -0.52
    ModelBuilder
    -0.52
     nahilalakip
    -0.51
     Scarlett
    -0.51
    igshid
    -0.51
     Barrie
    -0.50
     Dawes
    -0.50
    POSITIVE LOGITS
     DP
    1.37
     CP
    1.33
     BP
    1.30
    DP
    1.29
     RP
    1.29
    RP
    1.26
    BP
    1.25
     FP
    1.25
     HP
    1.24
    CP
    1.23
    Act Density 1.160%

    No Known Activations