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

    Neuronpedia

    INDEX
    Explanations

    dates and ordinals

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ভর্ত
    0.44
    स्कर
    0.42
     dobb
    0.42
    录取
    0.41
    네요
    0.41
     лучший
    0.40
    Ᏸ
    0.40
    நோ
    0.39
     protéines
    0.39
     是
    0.39
    POSITIVE LOGITS
    nationality
    0.43
     אטאטורק
    0.41
     Jazeera
    0.40
     Undang
    0.39
    huana
    0.39
    PRNewswire
    0.39
     Xinhua
    0.39
    Iranian
    0.39
    rendo
    0.38
     Macedonian
    0.38
    Act Density 0.001%

    No Known Activations