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

    Neuronpedia

    INDEX
    Explanations

    return statements and variable definitions in code-related contexts

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

    function arguments in parentheses

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Italijanski
    -0.73
    Diweddarwch
    -0.72
    WithIOException
    -0.63
     noDo
    -0.61
     AssemblyTitle
    -0.60
    }{*}{
    -0.58
     Италијани
    -0.57
    /**
    -0.57
    Espèce
    -0.56
    exitRule
    -0.54
    POSITIVE LOGITS
     intStringLen
    0.39
     slat
    0.33
    spec
    0.33
     MediatR
    0.32
     ligiloj
    0.32
    ird
    0.29
     للن
    0.29
    mainan
    0.29
     sound
    0.29
     Danish
    0.28
    Act Density 0.154%

    No Known Activations