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

    Neuronpedia

    INDEX
    Explanations

    specific time periods

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ς
    0.89
    syst
    0.85
    年代
    0.75
    िमम
    0.72
    లపై
    0.71
    cles
    0.71
    ंवर
    0.71
     фигу
    0.70
    ocyan
    0.70
    साइ
    0.70
    POSITIVE LOGITS
    OfWeek
    1.34
    tona
    1.32
     рождения
    1.31
    ചര്യ
    1.29
    dreams
    1.26
     féri
    1.22
    mares
    1.22
     стрелецкой
    1.22
    मर्रा
    1.21
     واللي
    1.20
    Act Density 0.295%

    No Known Activations