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

    Neuronpedia

    INDEX
    Explanations

    references to academic articles and their authors

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

    "Phys" after commas in citations

    np_acts-logits-general · gemini-2.0-flash

    physics journals and papers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    تقاوى
    -0.63
     True
    -0.52
    True
    -0.50
    ској
    -0.46
     kív
    -0.45
    albero
    -0.45
     JpaRepository
    -0.45
     TRUE
    -0.45
    ogenous
    -0.44
    MigrationBuilder
    -0.44
    POSITIVE LOGITS
     arXiv
    0.74
     arxiv
    0.71
     Phys
    0.71
    arXiv
    0.70
     physicists
    0.68
     Physics
    0.68
    Erstellt
    0.67
     fís
    0.67
     physics
    0.66
     físicos
    0.66
    Act Density 0.982%

    No Known Activations