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

    Neuronpedia

    INDEX
    Explanations

    behavior analysis

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    端口
    0.49
     (
    0.47
     Breakfast
    0.46
     Researcher
    0.45
     Packages
    0.45
     Glenn
    0.44
     acne
    0.44
     Young
    0.44
     down
    0.44
     Recipe
    0.44
    POSITIVE LOGITS
    cí
    0.52
    cích
    0.50
    t
    0.50
     certificados
    0.48
    訨
    0.48
     методи
    0.48
    pá
    0.48
    regar
    0.46
    貿
    0.46
     говорить
    0.46
    Act Density 0.000%

    No Known Activations