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

    Neuronpedia

    INDEX
    Explanations

    terms related to module and function passes in programming

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

    adapter, module, transformers, providers, Drawer

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     mo
    -0.36
     has
    -0.32
    log
    -0.30
     گیل
    -0.29
    ButterKnife
    -0.29
     log
    -0.29
     Log
    -0.29
     ger
    -0.29
    存于互联网档案馆
    -0.29
     f
    -0.28
    POSITIVE LOGITS
    ReusableCell
    0.77
    MigrationBuilder
    0.73
    WebServlet
    0.69
    parsedMessage
    0.68
    UserScript
    0.67
    DockStyle
    0.65
    fjspx
    0.65
    StructEnd
    0.64
     ſehr
    0.63
     propOrder
    0.63
    Act Density 0.206%

    No Known Activations