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

    Neuronpedia

    INDEX
    Explanations

    syntax elements or operators specific to programming languages

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

    "+" symbols in code or text

    np_acts-logits-general · gemini-2.0-flash

    C/C++ code additions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Italijani
    -0.82
     CWE
    -0.76
     <=",
    -0.67
    ESTRE
    -0.65
    NewGuid
    -0.64
    Према
    -0.63
    bukkit
    -0.61
     """",
    -0.59
    nodoc
    -0.59
     通販
    -0.57
    POSITIVE LOGITS
     Houſe
    0.66
     виправивши
    0.63
     entanto
    0.63
     itſelf
    0.63
    BeginContext
    0.62
    !*\
    0.60
     Jardim
    0.58
     дописавши
    0.58
    λέον
    0.58
     myſelf
    0.58
    Act Density 0.108%

    No Known Activations