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

    Neuronpedia

    INDEX
    Explanations

    using 'ing' or 'ize'

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     অবকাশ
    0.50
     그리고
    0.47
     begren
    0.47
    ."[
    0.46
     사
    0.45
     നാല
    0.45
    _;
    0.45
    čkom
    0.44
     وال
    0.43
    ."]
    0.43
    POSITIVE LOGITS
     perímetro
    0.45
    ጠቃ
    0.45
    يله
    0.44
     устройства
    0.43
    αι
    0.42
    ன்ப
    0.41
    பர்
    0.40
     Acer
    0.40
     сили
    0.40
     цель
    0.40
    Act Density 0.005%

    No Known Activations