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

    Neuronpedia

    INDEX
    Explanations

    Gemma model sizes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Gemini
    0.54
    Gem
    0.49
    აციის
    0.44
     GEM
    0.44
     Gem
    0.42
     hỗn
    0.40
     امنیت
    0.40
     ईमित्र
    0.40
    явления
    0.39
    тности
    0.39
    POSITIVE LOGITS
     தூ
    0.41
    褒
    0.36
     ഇറ
    0.35
     base
    0.35
     एज
    0.34
     departures
    0.34
    base
    0.34
     tè
    0.34
    ආ
    0.34
    anda
    0.33
    Act Density 0.009%

    No Known Activations