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

    Neuronpedia

    INDEX
    Explanations

    time or numerical ranges

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     nbsp
    0.56
     metaphor
    0.55
     కూ
    0.53
     Bern
    0.52
     Combined
    0.51
     ratio
    0.51
     জানেন
    0.51
     Skywalker
    0.51
     bs
    0.50
    عبير
    0.50
    POSITIVE LOGITS
    到
    2.41
     إلى
    2.26
     hingga
    2.24
     έως
    2.22
     đến
    2.13
     až
    2.13
     الى
    2.02
     到
    2.00
    ถึง
    1.96
    至
    1.94
    Act Density 0.731%

    No Known Activations