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

    Neuronpedia

    INDEX
    Explanations

    any intellectual task

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ROYAL
    0.43
    She
    0.40
    Her
    0.40
    σκεται
    0.39
     Her
    0.39
    েন্দ
    0.39
     Premium
    0.38
     prosecuting
    0.38
    োর্স
    0.37
     फर्जी
    0.37
    POSITIVE LOGITS
     програми
    0.41
    жением
    0.38
    庠
    0.38
     محمود
    0.37
    잖
    0.37
     patience
    0.37
     программы
    0.37
     factions
    0.37
     зрения
    0.36
     بدء
    0.36
    Act Density 0.000%

    No Known Activations