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

    Neuronpedia

    INDEX
    Explanations

    file path imports in code

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

    code paths

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ویکی‌پدی
    -0.55
     виправивши
    -0.54
     larmes
    -0.52
    httphttps
    -0.52
     مشين
    -0.51
    SourceChecksum
    -0.50
     noqa
    -0.49
    rawDesc
    -0.44
     snippetHide
    -0.43
    ThroughAttribute
    -0.41
    POSITIVE LOGITS
     subsystems
    0.60
     implementations
    0.60
     environments
    0.56
     wrappers
    0.55
     formulas
    0.53
     protocols
    0.53
     marketplaces
    0.53
     abstractions
    0.52
     subclasses
    0.52
     modules
    0.52
    Act Density 0.015%

    No Known Activations