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

    Neuronpedia

    INDEX
    Explanations

    plug in

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ني
    0.75
    b
    0.69
    štu
    0.67
    ס
    0.67
    ین
    0.66
    st
    0.65
    ق
    0.64
    ين
    0.64
    il
    0.62
    тку
    0.60
    POSITIVE LOGITS
    '
    0.80
     progression
    0.67
     blockchain
    0.67
     indexPath
    0.65
     homozygous
    0.63
     races
    0.60
     parameters
    0.60
     endurance
    0.60
     numerator
    0.59
     ایک
    0.58
    Act Density 0.002%

    No Known Activations