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

    Neuronpedia

    INDEX
    Explanations

    frequency and frequencies

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     sitio
    0.45
    рита
    0.43
     logro
    0.43
    ान
    0.42
    ريع
    0.42
    Ephemeral
    0.41
     Mecca
    0.41
    ىل
    0.40
     sitios
    0.39
    وتا
    0.39
    POSITIVE LOGITS
     urin
    0.46
     résident
    0.44
    延续
    0.42
     souten
    0.41
     연구
    0.41
     über
    0.40
     berk
    0.40
    בול
    0.40
     మ
    0.40
     Zeitschrift
    0.40
    Act Density 0.001%

    No Known Activations