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

    Neuronpedia

    INDEX
    Explanations

    medical abbreviations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    т
    0.91
    в
    0.77
     имат
    0.75
     briefings
    0.75
    ત
    0.74
     improvements
    0.73
     высокие
    0.73
     Dette
    0.72
    『
    0.71
    лери
    0.70
    POSITIVE LOGITS
    acteria
    0.96
    𝑈
    0.93
    uğ
    0.89
     petani
    0.88
     usuário
    0.87
    Baş
    0.86
    ując
    0.85
    ەڕ
    0.85
    ا
    0.84
    ری
    0.84
    Act Density 0.003%

    No Known Activations