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

    Neuronpedia

    INDEX
    Explanations

    frequently occurring terms and concepts

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

    most common or important items

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    RectangleBorder
    -0.65
     TestBed
    -0.59
    Tikang
    -0.57
    BeginContext
    -0.54
     Мексичка
    -0.50
     AssemblyCulture
    -0.49
    TypedDataSet
    -0.48
     '\\;'
    -0.48
     يتيمه
    -0.47
     تضيفلها
    -0.47
    POSITIVE LOGITS
    cipais
    0.50
     wichtigsten
    0.42
    Newswire
    0.41
     öne
    0.41
     common
    0.41
     principais
    0.40
     belangrijkste
    0.40
    dominant
    0.40
     fevere
    0.39
     principali
    0.38
    Act Density 0.090%

    No Known Activations