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

    Neuronpedia

    INDEX
    Explanations

    questions and summaries related to key recommendations or important findings

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

    summaries and key points

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     JpaRepository
    -0.74
    Autoritní
    -0.66
    сылкі
    -0.65
    Personensuche
    -0.64
     ویکی‌پدی
    -0.64
    GEBURTSDATUM
    -0.63
    avadoc
    -0.62
    MigrationBuilder
    -0.61
    TProtocol
    -0.61
    aarrggbb
    -0.61
    POSITIVE LOGITS
     summarized
    0.35
     summarised
    0.32
     notable
    0.31
     главных
    0.29
     zij
    0.28
     notably
    0.27
     principali
    0.27
     summary
    0.27
    Menurutnya
    0.27
     stated
    0.27
    Act Density 0.103%

    No Known Activations