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

    Neuronpedia

    INDEX
    Explanations

    defining math operations and comparisons

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     mathematical
    0.40
     पाई
    0.40
    बैंक
    0.40
     수학
    0.39
    ဆေး
    0.39
    gas
    0.38
     myCamera
    0.38
     mathematics
    0.38
     神
    0.38
    mathemat
    0.38
    POSITIVE LOGITS
     comparison
    0.49
    Comparison
    0.48
     Comparison
    0.44
    COMPAR
    0.41
    Floor
    0.41
     сравни
    0.40
    comparison
    0.40
    Compar
    0.39
     Floor
    0.39
     comparisons
    0.38
    Act Density 0.020%

    No Known Activations