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

    Neuronpedia

    INDEX
    Explanations

    certain words follow certain tokens

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     informacija
    0.46
     ಮಾಹಿತಿ
    0.46
     строку
    0.45
    cyber
    0.44
     ошибок
    0.44
     एसएस
    0.44
     ㅋㅋ
    0.43
     строка
    0.42
    ᄎ
    0.42
     помощ
    0.42
    POSITIVE LOGITS
     Heritage
    0.58
     Cultural
    0.55
    Holding
    0.50
    Midnight
    0.50
     Healthy
    0.48
     Midnight
    0.47
     Protective
    0.47
    Healthy
    0.47
    Heritage
    0.46
     heritage
    0.46
    Act Density 0.049%

    No Known Activations