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

    Neuronpedia

    INDEX
    Explanations

    created or designed

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     домаћинства
    0.53
     супер
    0.50
     базу
    0.48
     कुल
    0.48
     просмотра
    0.48
     кухни
    0.46
     просмо
    0.46
     воду
    0.45
     окна
    0.45
     cashback
    0.45
    POSITIVE LOGITS
    IND
    0.50
     Anatomy
    0.46
    şehir
    0.42
    ̃
    0.42
    选取
    0.41
     época
    0.39
    Geometry
    0.39
     Tri
    0.39
    ົບ
    0.38
    )
    0.38
    Act Density 0.006%

    No Known Activations