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

    Neuronpedia

    INDEX
    Explanations

    herbal medicine and remedies

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    as
    0.82
    ar
    0.73
    wrong
    0.72
    こと
    0.71
    it
    0.70
    त
    0.70
     wrong
    0.69
    но
    0.68
    arb
    0.66
     persen
    0.66
    POSITIVE LOGITS
    ulating
    0.72
     اعرف
    0.71
     clinging
    0.71
    ји
    0.70
    ্লিক
    0.70
     Оста
    0.69
    н
    0.69
    eep
    0.69
     ablaze
    0.69
    uruhan
    0.69
    Act Density 0.049%

    No Known Activations