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

    Neuronpedia

    INDEX
    Explanations

    there are / there were

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    har
    0.54
    data
    0.51
    ITIONS
    0.51
    class
    0.50
    model
    0.48
    podcast
    0.47
    el
    0.47
    test
    0.46
    heet
    0.46
    require
    0.46
    POSITIVE LOGITS
     пера
    0.53
     набу
    0.53
     заро
    0.50
     соору
    0.47
     возраст
    0.46
     паліты
    0.46
     крова
    0.46
    даг
    0.46
     руба
    0.45
     siy
    0.45
    Act Density 0.000%

    No Known Activations