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

    Neuronpedia

    INDEX
    Explanations

    programming constructs and syntax elements in code

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

    Code snippets using math functions or standard input/output

    np_acts-logits-general · gemini-2.0-flash

    C++ `std` and `Math` functions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    性は
    -0.55
    性に
    -0.52
    ╛
    -0.51
    andria
    -0.50
    PRT
    -0.49
    RG
    -0.49
     воз
    -0.49
    話は
    -0.48
    CHRE
    -0.48
     الأخيرة
    -0.48
    POSITIVE LOGITS
    findpost
    0.97
    parsedMessage
    0.93
     EconPapers
    0.90
     GenerationType
    0.89
     المعيارى
    0.85
    uxxxx
    0.83
    VersionUID
    0.83
    ValueStyle
    0.82
    WithIOException
    0.79
    MemoryWarning
    0.79
    Act Density 0.214%

    No Known Activations