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

    Neuronpedia

    INDEX
    Explanations

    time units, attempts, quantity

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     શ્રી
    0.42
     巴
    0.41
     ""),
    0.41
     पैसा
    0.40
    erg
    0.39
    euro
    0.38
    backer
    0.37
     kose
    0.36
    bas
    0.36
     উঠছে
    0.36
    POSITIVE LOGITS
     days
    0.49
     years
    0.47
    days
    0.44
     seconds
    0.41
     weeks
    0.40
    Days
    0.40
    Years
    0.39
     secs
    0.39
     DAYS
    0.38
    ⁉
    0.38
    Act Density 0.002%

    No Known Activations