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

    Neuronpedia

    INDEX
    Explanations

    name

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ដែល
    1.04
     grec
    1.02
    饮
    1.02
     酒
    1.01
    其
    1.01
    ार्क
    0.99
     已
    0.98
    证券
    0.98
     判断
    0.98
     对象
    0.98
    POSITIVE LOGITS
    ral
    0.94
    ed
    0.92
    anse
    0.92
    urnal
    0.90
    al
    0.90
    ren
    0.90
    rem
    0.88
    rup
    0.86
     bulldoz
    0.86
    ing
    0.85
    Act Density 0.030%

    No Known Activations