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

    Neuronpedia

    INDEX
    Explanations

    spatial locations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Ahead
    0.42
     Ahead
    0.40
     luật
    0.38
     розта
    0.38
    raquo
    0.38
    лянчук
    0.37
    篒
    0.37
    在家
    0.36
     गति
    0.36
    გენ
    0.35
    POSITIVE LOGITS
     bottom
    1.40
     underside
    1.30
     sides
    1.22
     upper
    1.20
    bottom
    1.13
     top
    1.12
    底部
    1.07
     outer
    1.02
    底
    0.98
     bottoms
    0.96
    Act Density 0.139%

    No Known Activations