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

    Neuronpedia

    INDEX
    Explanations

    structural elements of programming code such as brackets, semicolons, and expressions

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

    user content

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Holder
    -0.48
    ABASE
    -0.47
     Holders
    -0.41
    SAE
    -0.41
    seku
    -0.40
    Подготовка
    -0.40
    Préparation
    -0.40
     gathering
    -0.40
    Footnotes
    -0.39
    makedirs
    -0.39
    POSITIVE LOGITS
    تقاوى
    0.53
    sizeCache
    0.53
     searched
    0.53
     poveznice
    0.50
    expandindo
    0.50
    contentLoaded
    0.49
     propOrder
    0.49
    isContained
    0.49
    GEBURTSDATUM
    0.48
     defaultstate
    0.48
    Act Density 0.013%

    No Known Activations