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

    Neuronpedia

    INDEX
    Explanations

    structured information and methodologies in data analysis

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

    introducing explanations or results

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     SAU
    -0.41
     /\.(
    -0.41
    Datuak
    -0.40
    inSlope
    -0.40
    الإنجليزية
    -0.40
     CARS
    -0.40
    nextLine
    -0.38
     CUR
    -0.38
    +/*
    -0.37
     farlo
    -0.37
    POSITIVE LOGITS
    tagHelperRunner
    0.52
    awtextra
    0.52
    contentLoaded
    0.46
     StatelessWidget
    0.45
    ativement
    0.45
     مشارکت‌کنندگان
    0.43
     تضيفلها
    0.43
    TableAdapter
    0.43
    :✨
    0.42
     vertrou
    0.41
    Act Density 0.126%

    No Known Activations