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

    Neuronpedia

    INDEX
    Explanations

    programming syntax elements such as function calls and semicolons

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

    Code-related syntax (brackets, semicolons, etc.)

    np_acts-logits-general · gemini-2.0-flash

    list of integers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     betweenstory
    -1.01
    StoryboardSegue
    -0.97
     nahilalakip
    -0.96
     '\\;'
    -0.90
    MemoryWarning
    -0.88
    GraphicsUnit
    -0.87
    parsedMessage
    -0.81
     GreatSchools
    -0.81
     Paglinawan
    -0.80
     ویکی‌پدیا
    -0.79
    POSITIVE LOGITS
    æus
    0.58
    二是
    0.51
    dorfer
    0.47
    getVar
    0.47
     cry
    0.46
    jaer
    0.44
    føring
    0.44
    vikle
    0.43
    skrift
    0.43
     sebaliknya
    0.43
    Act Density 0.162%

    No Known Activations