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

    Neuronpedia

    INDEX
    Explanations

    cloud provider resources

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ধানা
    0.76
    ycznych
    0.66
     역시
    0.64
     खतरा
    0.63
    amples
    0.62
     গ্রামে
    0.61
    ებულია
    0.61
    ósticos
    0.61
     Гру
    0.60
     Ở
    0.60
    POSITIVE LOGITS
     hybrid
    0.60
     suisse
    0.60
    buenas
    0.59
    ่อ
    0.58
     quand
    0.57
     ощу
    0.55
     officials
    0.55
     swiss
    0.55
    번에
    0.55
     transitional
    0.54
    Act Density 0.002%

    No Known Activations