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

    Neuronpedia

    INDEX
    Explanations

    exponent notation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     inspiration
    0.22
     SAS
    0.20
    भा
    0.20
     luggage
    0.20
    acom
    0.20
     Inspiration
    0.20
     Pop
    0.20
     Daphne
    0.20
    Promo
    0.19
     Dore
    0.19
    POSITIVE LOGITS
    fifth
    0.21
     брен
    0.21
     ціка
    0.20
    ಿತ್ತು
    0.20
    북도
    0.20
    ρέ
    0.19
     fün
    0.19
    締め
    0.19
     سرعت
    0.19
     walaupun
    0.19
    Act Density 0.006%

    No Known Activations