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

    Neuronpedia

    INDEX
    Explanations

    roman installment

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    కు
    0.49
    空
    0.49
     માત્ર
    0.48
     клави
    0.46
     кнопки
    0.44
     машины
    0.43
     между
    0.43
    岭
    0.43
     пре
    0.43
     цвето
    0.42
    POSITIVE LOGITS
    َّة
    0.48
    ̣t
    0.48
     مفید
    0.47
    ังสือ
    0.46
    सूचित
    0.46
     dioxane
    0.45
     تفصیل
    0.44
     giants
    0.43
     purified
    0.43
     Shapiro
    0.43
    Act Density 0.002%

    No Known Activations