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

    Neuronpedia

    INDEX
    Explanations

    occurrences of access modifiers in code, specifically 'private', 'public', and 'protected'

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

    C++ or C# keywords

    np_acts-logits-general · gemini-2.0-flash

    programming keywords and code structure

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    MLLoader
    -0.72
     autorytatywna
    -0.70
    archiviato
    -0.68
    SizeMode
    -0.66
    peutic
    -0.65
    — 
    -0.65
    ">:
    -0.65
     فريبيس
    -0.65
     مرئيه
    -0.64
    )”
    -0.63
    POSITIVE LOGITS
    private
    1.00
    expandindo
    0.83
    public
    0.80
     private
    0.62
     public
    0.59
    ↵↵
    0.58
    protected
    0.53
    constructor
    0.49
    endregion
    0.49
    newInstance
    0.47
    Act Density 0.035%

    No Known Activations