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

    Neuronpedia

    INDEX
    Explanations

    terminology related to pairs and pairings

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

    foreign key-value pairs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    存于互联网档案馆
    -0.74
     Савезне
    -0.65
    RenderAtEndOf
    -0.63
     Administrativna
    -0.62
     surla
    -0.60
     مرئيه
    -0.60
     ویکی‌پدی
    -0.59
    StructEnd
    -0.57
     utafitiHapana
    -0.57
    Хьажоргаш
    -0.57
    POSITIVE LOGITS
     pair
    0.56
     pairs
    0.53
     paired
    0.49
    pair
    0.48
     Pair
    0.47
     paire
    0.46
    Pair
    0.45
    optionalTypeArgs
    0.43
     pairing
    0.41
     Pairs
    0.41
    Act Density 0.001%

    No Known Activations