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

    Neuronpedia

    INDEX
    Explanations

    numbers, particularly quantities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ører
    0.52
     dices
    0.52
     decom
    0.50
     veden
    0.50
    л
    0.49
     lysosomes
    0.48
     gerek
    0.47
     deodor
    0.47
    к
    0.47
     computing
    0.47
    POSITIVE LOGITS
    five
    0.59
     दरम्यान
    0.56
    four
    0.52
    中に
    0.51
    grid
    0.50
    six
    0.49
     ज्यात
    0.47
    均为
    0.46
    popular
    0.46
     त्यानुसार
    0.45
    Act Density 0.000%

    No Known Activations