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

    Neuronpedia

    INDEX
    Explanations

    situations involving doors, windows, and their states of being open or closed

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

    door and window states

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    -0.62
     препратки
    -0.61
     الحره
    -0.59
     المعيارى
    -0.57
    RenderAtEndOf
    -0.57
     ArrayAdapter
    -0.57
     مشين
    -0.57
    ⤹
    -0.55
    Cyfarwyddwr
    -0.55
     Wikimedijinoj
    -0.52
    POSITIVE LOGITS
    enterOuterAlt
    0.35
     bev
    0.33
     lock
    0.30
    Dil
    0.29
     locked
    0.29
     rated
    0.29
     diluted
    0.29
    unlocked
    0.28
    kWh
    0.27
    шаго
    0.27
    Act Density 0.105%

    No Known Activations