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

    Neuronpedia

    INDEX
    Explanations

    non-English words

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    হারে
    0.66
     capitaine
    0.63
    лимп
    0.63
     izra
    0.62
    ವರಿಗೆ
    0.60
    ্বরের
    0.60
    ዃ
    0.59
    উনি
    0.58
     namen
    0.58
    грама
    0.58
    POSITIVE LOGITS
    readyState
    0.68
     जाए
    0.63
    僉
    0.57
    访问
    0.56
    garde
    0.55
    懿
    0.55
    util
    0.55
     воспользова
    0.54
     Cont
    0.54
    ภาพ
    0.52
    Act Density 0.000%

    No Known Activations