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

    Neuronpedia

    INDEX
    Explanations

    energy and coding

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Hồ
    1.19
     läbi
    1.10
    ⎣
    1.09
     فلا
    1.08
    рна
    1.08
    авто
    1.07
     Сы
    1.07
     Agar
    1.07
     Tiger
    1.06
     llegada
    1.06
    POSITIVE LOGITS
    forEach
    1.14
    yes
    1.11
    notch
    1.10
    𝐠
    1.10
    have
    1.09
    yard
    1.08
    cities
    1.08
     gaskets
    1.06
    𝐫
    1.06
    calorie
    1.05
    Act Density 0.017%

    No Known Activations