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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "this" and code-related syntax elements

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

    code structure

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    rawDesc
    -0.54
     كومونز
    -0.49
     scu
    -0.48
    nextProps
    -0.46
    QueryBuilder
    -0.46
    bori
    -0.46
     חיצוניים
    -0.45
    oneg
    -0.44
    cipar
    -0.44
     squ
    -0.44
    POSITIVE LOGITS
     SafeMath
    0.43
     propOrder
    0.41
     Autorisations
    0.39
     <>",
    0.36
     informée
    0.35
     emperador
    0.35
     anhänger
    0.35
    MessageOf
    0.35
    حياتها
    0.35
    NameInMap
    0.35
    Act Density 0.003%

    No Known Activations