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

    Neuronpedia

    INDEX
    Explanations

    conjunctions and punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    è
    0.43
     bijvoorbeeld
    0.40
     esimerkiksi
    0.40
     ossia
    0.40
    page
    0.40
    érie
    0.40
     very
    0.39
    nač
    0.38
     cioè
    0.38
    umont
    0.38
    POSITIVE LOGITS
     позволяет
    0.64
     உதவுக
    0.61
     ensures
    0.61
     позволит
    0.61
     allows
    0.58
     предотвра
    0.56
    Allows
    0.56
     обеспечивает
    0.54
     позволя
    0.54
     Allows
    0.53
    Act Density 0.049%

    No Known Activations