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

    Neuronpedia

    INDEX
    Explanations

    words from different languages

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    4
    0.37
    自分で
    0.33
    8
    0.32
     Deutschland
    0.31
     asing
    0.30
     Voici
    0.30
     USING
    0.29
     siehe
    0.29
    3
    0.29
    eBay
    0.29
    POSITIVE LOGITS
     meski
    0.39
     подобных
    0.38
     গেলেও
    0.35
     প্রমুখ
    0.34
    )+"]
    0.34
     hasonló
    0.34
     bárm
    0.34
    🤞
    0.34
     সামগ্র
    0.34
     마무리
    0.34
    Act Density 0.097%

    No Known Activations