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

    Neuronpedia

    INDEX
    Explanations

    code and explanations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    без
    0.45
    Без
    0.43
     senza
    0.41
     subpoenas
    0.41
     lobbyists
    0.41
     без
    0.39
     without
    0.38
    )=-
    0.38
    צע
    0.38
     nélkül
    0.38
    POSITIVE LOGITS
     ','
    0.41
     Solubility
    0.41
     There
    0.40
     Découvrez
    0.40
     '.'
    0.38
     "}
    0.38
    querySelector
    0.38
     Prä
    0.38
     ໜອງ
    0.38
    '{
    0.38
    Act Density 0.001%

    No Known Activations