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

    Neuronpedia

    INDEX
    Explanations

    references to academic authors and their affiliations

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

    research paper disclosures and authorship

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     تضيفلها
    -0.38
    ValueStyle
    -0.34
    tagPool
    -0.33
     Benav
    -0.33
     uits
    -0.31
     réalité
    -0.31
     wortel
    -0.30
     mezzi
    -0.30
    מבר
    -0.30
     altrett
    -0.30
    POSITIVE LOGITS
    transQ
    0.70
    OGND
    0.50
    évaluateur
    0.48
    tvguidetime
    0.48
     Researcher
    0.48
    참고
    0.47
     yyb
    0.47
    SpringRunner
    0.47
    RefNanny
    0.47
    ManagedBean
    0.47
    Act Density 0.207%

    No Known Activations