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

    Neuronpedia

    INDEX
    Explanations

    dampness and cold

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    у
    0.59
    وض
    0.47
    람
    0.45
    ع
    0.44
     compromise
    0.44
    說明
    0.43
    ีย
    0.42
    ادم
    0.41
    ª
    0.41
    ثم
    0.41
    POSITIVE LOGITS
     ঈশ্বর
    0.52
    erçe
    0.50
     граф
    0.49
     бю
    0.49
     لین
    0.48
     गे
    0.47
    ເທ
    0.47
     ด้วย
    0.46
    esu
    0.46
     叶
    0.46
    Act Density 0.006%

    No Known Activations