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

    Neuronpedia

    INDEX
    Explanations

    sauces and ingredients

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    rows
    0.51
    WeekDates
    0.46
    weight
    0.45
     وتع
    0.44
    asını
    0.44
     unsere
    0.44
     خواهند
    0.43
     et
    0.43
     ઘ
    0.42
     ውጤ
    0.42
    POSITIVE LOGITS
    흄
    0.47
    lüssel
    0.46
     paradig
    0.45
    ல்லை
    0.45
    觐
    0.45
    리스
    0.43
    रसा
    0.43
     Sains
    0.43
     Cambio
    0.42
    전
    0.42
    Act Density 0.002%

    No Known Activations