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

    Neuronpedia

    INDEX
    Explanations

    conjunctions and subsequent actions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     There
    0.22
     بوده
    0.21
     není
    0.21
     is
    0.21
     nejsou
    0.20
     inklusive
    0.20
     anty
    0.20
    !=
    0.20
     mohou
    0.20
     edhe
    0.19
    POSITIVE LOGITS
     put
    0.23
    ari
    0.22
    ppsala
    0.22
     அதை
    0.21
     decide
    0.20
    それを
    0.20
    rog
    0.20
    ijer
    0.20
    rt
    0.20
     попыта
    0.19
    Act Density 0.399%

    No Known Activations