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

    Neuronpedia

    INDEX
    Explanations

    ES modules and ES6+

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     resource
    0.51
     resources
    0.47
    资源
    0.46
    資源
    0.46
     ресурс
    0.45
     ресурсов
    0.45
     ressources
    0.43
    资源的
    0.42
    袂
    0.41
     ресурсы
    0.40
    POSITIVE LOGITS
    class
    0.51
     class
    0.44
     класс
    0.41
    iterations
    0.40
    Class
    0.40
     öffent
    0.39
    classes
    0.39
     புதிய
    0.39
     клас
    0.39
    formats
    0.38
    Act Density 0.003%

    No Known Activations