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

    Neuronpedia

    INDEX
    Explanations

    prime factorization

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Saunders
    -0.06
    ":[{"
    -0.06
     taşın
    -0.06
    Provid
    -0.06
     '),
    -0.06
     Champions
    -0.06
     li
    -0.06
    anto
    -0.06
     Mori
    -0.06
    tls
    -0.06
    POSITIVE LOGITS
     постро
    0.07
     döneminde
    0.06
     girişim
    0.06
     sır
    0.06
     overlapping
    0.06
     Venice
    0.06
     béné
    0.06
     иде
    0.06
     >::
    0.06
     применения
    0.06
    Act Density 0.056%

    No Known Activations