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

    Neuronpedia

    INDEX
    Explanations

    specific terms related to data, information, and research processes

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

    all nouns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ujednoznacz
    -0.79
    Хьажоргаш
    -0.44
    bufio
    -0.42
    ologue
    -0.40
     few
    -0.40
     Alembic
    -0.40
    บาง
    -0.40
    mitten
    -0.40
    Билгалдахарш
    -0.39
    few
    -0.38
    POSITIVE LOGITS
     모든
    0.77
     everything
    0.76
     Semua
    0.73
     wszystkie
    0.71
    すべての
    0.70
     EVERYTHING
    0.70
     تمامی
    0.68
     todas
    0.67
     semua
    0.67
     tüm
    0.65
    Act Density 0.379%

    No Known Activations