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

    Neuronpedia

    INDEX
    Explanations

    elements related to programming structures and data types

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

    prefix "The" or "user"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    yarnpkg
    -0.64
    +#+#
    -0.62
    iastes
    -0.56
     ddelweddau
    -0.55
    armament
    -0.54
    msgTypes
    -0.52
    astéro
    -0.52
     فريبيس
    -0.51
     Réponses
    -0.51
     tartalomajánló
    -0.50
    POSITIVE LOGITS
    input
    0.47
     represents
    0.45
     sebuah
    0.42
     The
    0.42
     the
    0.41
     merupakan
    0.40
     Sebuah
    0.40
     is
    0.40
    the
    0.39
     must
    0.39
    Act Density 0.025%

    No Known Activations