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

    Neuronpedia

    INDEX
    Explanations

    percentages and scores

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ১৬
    0.44
    १८
    0.39
     Thirteen
    0.35
    १८४
    0.34
     thirteen
    0.34
     dedic
    0.32
    தன
    0.32
     ১৩
    0.31
    atangan
    0.31
    ১৩
    0.31
    POSITIVE LOGITS
    десят
    0.43
    <unused2166>
    0.38
     maanden
    0.37
     meses
    0.36
    <unused2126>
    0.36
     miesięcy
    0.36
     months
    0.36
    5
    0.36
     месяцев
    0.35
     mesi
    0.35
    Act Density 0.017%

    No Known Activations