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

    Neuronpedia

    INDEX
    Explanations

    binomial coefficients

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    fall
    0.43
    segment
    0.42
    parcel
    0.42
    Utilization
    0.42
    backend
    0.41
    Ό
    0.41
    ),
    0.41
    veil
    0.41
     macros
    0.40
    лл
    0.39
    POSITIVE LOGITS
     Essex
    0.46
     Mohamed
    0.43
    ನಗೆ
    0.43
     Mahama
    0.43
     Monsoon
    0.43
     Dharma
    0.42
     Brunei
    0.42
     Yoruba
    0.42
     Anakin
    0.41
     Dhaka
    0.41
    Act Density 0.009%

    No Known Activations