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

    Neuronpedia

    INDEX
    Explanations

    references to categories and their hierarchical structures in programming code

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

    category, categories, and classification

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    RenderAtEndOf
    -0.54
    SourceChecksum
    -0.53
    Diwedd
    -0.51
    zzar
    -0.50
    esgue
    -0.49
    issory
    -0.49
    __(/*!
    -0.48
    Configurer
    -0.48
     Италијани
    -0.48
    逅
    -0.47
    POSITIVE LOGITS
     category
    0.82
     categories
    0.82
     categorization
    0.69
    categories
    0.68
    category
    0.66
     Categories
    0.65
     categorize
    0.64
     Category
    0.63
     categoria
    0.62
     classification
    0.60
    Act Density 0.029%

    No Known Activations