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

    Neuronpedia

    INDEX
    Explanations

    quantities and comparisons

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Agreement
    0.45
    son
    0.41
     Jiang
    0.40
     Chance
    0.39
     Opportunity
    0.39
     Leslie
    0.38
     Guillaume
    0.38
    sp
    0.38
     Agarwal
    0.38
     Zaman
    0.37
    POSITIVE LOGITS
     količ
    0.46
     sayıda
    0.44
     amounts
    0.41
     количество
    0.41
    ﺩ
    0.39
    ቶችን
    0.38
    р
    0.38
     amount
    0.37
    更多的
    0.36
     quantità
    0.36
    Act Density 0.202%

    No Known Activations