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

    Neuronpedia

    INDEX
    Explanations

    references to academic or publishing information, particularly related to books and articles

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

    titles and publication information of books or articles

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

    citations like id. and at

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ngdoc
    -0.75
    Twas
    -0.70
     Autorizaciones
    -0.69
    zwald
    -0.63
     Shakspeare
    -0.62
    ték
    -0.62
     ffilmiau
    -0.62
     commerciaux
    -0.61
    PhysRev
    -0.60
    RTEX
    -0.60
    POSITIVE LOGITS
     passim
    0.76
     argues
    0.64
     argued
    0.56
     argue
    0.54
     sobretudo
    0.53
    ariste
    0.53
     arguing
    0.52
     convincingly
    0.50
    rmtree
    0.49
     scholarship
    0.48
    Act Density 0.065%

    No Known Activations