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

    Neuronpedia

    INDEX
    Explanations

    mathematical terms, efficiency, explanation structure

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     rivers
    0.43
     magnetite
    0.41
     array
    0.40
     permeate
    0.38
     innumerable
    0.37
     cooper
    0.37
     multilevel
    0.37
     oats
    0.37
     interrelated
    0.37
     arrays
    0.37
    POSITIVE LOGITS
     Sempre
    0.44
     سمع
    0.41
     فع
    0.41
    ండో
    0.40
    说什么
    0.40
    Image
    0.38
    會在
    0.38
    响应文件
    0.38
    ப்புகளில்
    0.38
    业绩
    0.37
    Act Density 0.000%

    No Known Activations