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

    Neuronpedia

    INDEX
    Explanations

    basic, básico, basic rules

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Глав
    0.48
     главной
    0.43
     仕
    0.37
     Глав
    0.37
    দ্ম
    0.37
    পূর্বক
    0.35
    沍
    0.35
     глав
    0.34
     thoáng
    0.34
     голов
    0.33
    POSITIVE LOGITS
     basic
    4.22
    Basic
    4.00
     Basic
    3.98
    basic
    3.98
    基本
    3.73
     básico
    3.45
     básica
    3.39
    BASIC
    3.39
     BASIC
    3.38
     बेसिक
    3.34
    Act Density 0.161%

    No Known Activations