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

    Neuronpedia

    INDEX
    Explanations

    domains and communities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    اد
    0.81
    စီ
    0.77
    دهای
    0.76
    żej
    0.73
    áter
    0.73
    тер
    0.73
    ilizce
    0.73
    ه‌ها
    0.72
    ро
    0.70
    ه‌های
    0.70
    POSITIVE LOGITS
     philanthrop
    0.91
    における
    0.88
     itself
    0.81
     signified
    0.77
    において
    0.77
    QueryParams
    0.76
     சார்பில்
    0.76
     quo
    0.75
     represented
    0.73
     undeniably
    0.73
    Act Density 0.494%

    No Known Activations