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

    Neuronpedia

    INDEX
    Explanations

    what has or e.what()

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     புதி
    0.72
    പ്ര
    0.69
     இடம்பெ
    0.68
    ration
    0.67
    स्तर
    0.67
     değişik
    0.67
    새
    0.67
    ideo
    0.67
     medición
    0.67
     새로
    0.66
    POSITIVE LOGITS
     upholding
    0.69
    ในช่วง
    0.66
     Netherlands
    0.65
    Taste
    0.64
     followed
    0.64
     binds
    0.62
     Italy
    0.61
    WW
    0.61
     fostering
    0.61
     Itália
    0.61
    Act Density 0.004%

    No Known Activations