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

    Neuronpedia

    INDEX
    Explanations

    khoảng, khối, khả

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    website
    0.49
    world
    0.43
    repo
    0.43
    decorators
    0.43
    mand
    0.42
    iss
    0.42
    淪
    0.42
    king
    0.42
    rumah
    0.42
    riet
    0.41
    POSITIVE LOGITS
    ảng
    0.47
     Exploring
    0.41
     Definitions
    0.41
     Definition
    0.40
     Edited
    0.39
     Aldo
    0.38
     luxury
    0.38
     定义
    0.38
    翅
    0.38
     examining
    0.37
    Act Density 0.001%

    No Known Activations