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

    Neuronpedia

    INDEX
    Explanations

    military usage and services

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     are
    0.61
    의
    0.47
    נו
    0.47
    4
    0.46
     synergy
    0.45
    계
    0.45
     медве
    0.44
    약
    0.44
    are
    0.43
     compares
    0.43
    POSITIVE LOGITS
     मान्यता
    0.43
     थांब
    0.42
     जिम्मेदारी
    0.42
     responsabilité
    0.40
    本身
    0.40
    ्‍यादा
    0.40
    commision
    0.39
    最好
    0.38
    ٹرول
    0.38
    倌
    0.38
    Act Density 0.003%

    No Known Activations