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

    Neuronpedia

    INDEX
    Explanations

    instances of specific programming constructs or patterns

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

    code and technical documentation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     للاسماء
    -0.78
    ########.
    -0.72
    Personendaten
    -0.66
    ViewImports
    -0.62
    complexContent
    -0.59
     שוליים
    -0.56
    SharedCtor
    -0.55
    IsContent
    -0.55
    ciatore
    -0.54
    djangoproject
    -0.54
    POSITIVE LOGITS
    tagHelperRunner
    0.40
    {{\
    0.31
    <<<<<<<
    0.28
     naro
    0.28
     /*#__
    0.28
    ','#
    0.28
    Berry
    0.28
     Wahrheit
    0.27
    แอ
    0.27
    ORAGE
    0.27
    Act Density 0.308%

    No Known Activations