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

    Neuronpedia

    INDEX
    Explanations

    references to specific numerical data and metrics

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

    legal cases and citations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ########.
    -0.66
    ⮕
    -0.63
    HostException
    -0.62
    tanleria
    -0.61
    ंदीखरीदारी
    -0.60
    BibitemShut
    -0.60
     المعيارى
    -0.57
    səhifə
    -0.57
     <>",
    -0.57
    <unused41>
    -0.56
    POSITIVE LOGITS
    PreferredItem
    0.39
    发表于
    0.35
    S
    0.29
     initComponents
    0.28
    zensionen
    0.28
    Place
    0.27
     Lev
    0.27
    BackStack
    0.27
    V
    0.27
     v
    0.27
    Act Density 0.055%

    No Known Activations