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

    Neuronpedia

    INDEX
    Explanations

    people's names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     MATLAB
    0.45
     ఉన్నాయి
    0.43
     оно
    0.43
    它们的
    0.43
    Generate
    0.43
     ఉంటాయి
    0.42
     которое
    0.42
     ஆகியவை
    0.42
    它們
    0.42
    它
    0.42
    POSITIVE LOGITS
     himself
    1.33
     who
    1.10
     ಅವರ
    1.04
     Jr
    1.02
     quien
    1.01
     ಅವರು
    0.97
     whom
    0.96
     oversaw
    0.92
     แห่ง
    0.90
    who
    0.89
    Act Density 0.319%

    No Known Activations