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

    Neuronpedia

    INDEX
    Explanations

    mathematical operations and expressions

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

    mathematical equations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Setup
    -0.36
     hub
    -0.35
    Content
    -0.34
     pauvreté
    -0.33
     Calab
    -0.33
    Inventory
    -0.32
    Invert
    -0.32
     mirror
    -0.32
     search
    -0.32
    Status
    -0.32
    POSITIVE LOGITS
    expandindo
    0.81
     للاسماء
    0.77
    verwijspagina
    0.64
    Personendaten
    0.63
    الحياه
    0.63
    WithIOException
    0.62
    :✨
    0.61
    ArrowToggle
    0.61
     EconPapers
    0.61
     Biôgrafia
    0.60
    Act Density 0.505%

    No Known Activations