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

    Neuronpedia

    INDEX
    Explanations

    references to the concepts of "first" and "second"

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

    first, second, third, fourth

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     مشين
    -0.75
     المعيارى
    -0.68
    featureID
    -0.66
     ProtoMessage
    -0.64
    MLLoader
    -0.63
     laſſen
    -0.60
    TagMode
    -0.58
    存于互联网档案馆
    -0.56
     iNdEx
    -0.55
     Chwiliwch
    -0.54
    POSITIVE LOGITS
    Second
    0.64
     Second
    0.57
    First
    0.57
    Third
    0.54
     First
    0.52
     SECOND
    0.50
     Third
    0.47
    SECOND
    0.45
    Half
    0.45
     Segunda
    0.43
    Act Density 0.024%

    No Known Activations