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

    Neuronpedia

    INDEX
    Explanations

    hungarian words and suffixes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     национа
    0.72
     Ти
    0.70
     одного
    0.68
     Кри
    0.68
     Национа
    0.66
     выше
    0.66
     Hungarian
    0.65
     Из
    0.65
    瑗
    0.65
    ские
    0.64
    POSITIVE LOGITS
    az
    0.84
    ot
    0.80
    ni
    0.78
     és
    0.78
    ell
    0.77
    ér
    0.76
    ív
    0.76
    ett
    0.76
     egy
    0.75
    uk
    0.74
    Act Density 0.009%

    No Known Activations