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

    Neuronpedia

    INDEX
    Explanations

    locations and countries

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ๎
    0.18
     яе
    0.17
     LINKS
    0.17
     Thats
    0.17
    それが
    0.16
     nje
    0.16
     stronę
    0.16
    それを
    0.15
    ܤ
    0.15
     tajem
    0.15
    POSITIVE LOGITS
    央
    0.14
    蒸
    0.14
    vstack
    0.14
    лни
    0.13
     اک
    0.13
    </
    0.13
    确实
    0.13
    欧洲
    0.13
    orche
    0.13
     ECL
    0.13
    Act Density 0.003%

    No Known Activations