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

    Neuronpedia

    INDEX
    Explanations

    technical terms and code-related syntax, particularly related to programming and commands

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

    compiler flags

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    VYMaps
    -0.60
    +#+#
    -0.60
    DoubleQuotes
    -0.56
     незавершена
    -0.56
     للمعارف
    -0.56
     surla
    -0.54
    ]=>
    -0.50
    \{\\
    -0.49
     bezeichneter
    -0.48
     Deserialize
    -0.47
    POSITIVE LOGITS
     strict
    0.60
    Strict
    0.49
     estric
    0.47
    strict
    0.46
     AssemblyCulture
    0.43
     Strict
    0.43
    StrictMode
    0.41
     ſever
    0.39
     stricter
    0.38
     tranſ
    0.35
    Act Density 0.009%

    No Known Activations