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

    Neuronpedia

    INDEX
    Explanations

    high index in sorting

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    between
    0.71
     like
    0.70
     alleys
    0.63
    fores
    0.63
    Restaurants
    0.62
    ounces
    0.60
    owns
    0.60
    gar
    0.59
    bab
    0.58
    like
    0.58
    POSITIVE LOGITS
     as
    0.99
    дения
    0.97
     както
    0.89
    ன்படி
    0.86
     તરીકે
    0.86
     результатов
    0.85
    ରେ
    0.85
     результа
    0.85
     результаты
    0.85
    为例
    0.84
    Act Density 0.002%

    No Known Activations