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

    Neuronpedia

    INDEX
    Explanations

    references to flat surfaces or objects

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

    flat descriptor

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     queſta
    -0.64
     eventName
    -0.62
     endIndex
    -0.60
     eventId
    -0.58
     pouvoit
    -0.56
    뀜
    -0.56
     bookId
    -0.55
     userDao
    -0.55
     quæ
    -0.55
     ſind
    -0.54
    POSITIVE LOGITS
     flat
    2.11
     Flat
    2.03
    Flat
    1.98
    flat
    1.97
     FLAT
    1.90
    FLAT
    1.72
     flats
    1.40
     Flats
    1.28
    flats
    1.26
    フラット
    1.15
    Act Density 0.005%

    No Known Activations