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

    Neuronpedia

    INDEX
    Explanations

    numbers, quantities, durations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    řejmě
    0.34
    䡒
    0.31
     ①
    0.29
    dueDate
    0.29
    ونه
    0.29
    क्राइब
    0.28
    েন্স
    0.28
     పు
    0.27
    辄
    0.27
    ObjectMapper
    0.27
    POSITIVE LOGITS
    th
    0.71
     months
    0.61
     seater
    0.57
     सदस्यीय
    0.56
     दिवसीय
    0.54
     minutes
    0.52
     minute
    0.51
     meses
    0.51
     maanden
    0.51
     month
    0.50
    Act Density 0.085%

    No Known Activations