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

    Neuronpedia

    INDEX
    Explanations

    technical terms after 'de'

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    en
    0.89
    ed
    0.81
    es
    0.81
    ing
    0.76
    ة
    0.76
    os
    0.75
    eti
    0.75
    0.69
    PickerController
    0.67
    eine
    0.66
    POSITIVE LOGITS
    ꞎ
    0.70
    ផ្គ
    0.62
    퐫
    0.61
    <unused1807>
    0.61
    xq
    0.60
    σουν
    0.60
    φό
    0.59
    শোধ
    0.59
    τής
    0.59
     шаблон
    0.59
    Act Density 0.023%

    No Known Activations