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

    Neuronpedia

    INDEX
    Explanations

    phrases starting with "starts"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ítő
    0.41
    кую
    0.40
    áculo
    0.40
    upu
    0.39
    angebot
    0.39
    inue
    0.39
    ếc
    0.39
    chief
    0.38
    чыць
    0.38
     হব
    0.37
    POSITIVE LOGITS
     Qualcomm
    0.43
     MNIST
    0.42
    మ్‌
    0.41
     وقع
    0.41
     stemming
    0.41
     notion
    0.41
     hangar
    0.41
     Adidas
    0.40
     urgente
    0.40
     Sony
    0.40
    Act Density 0.002%

    No Known Activations