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

    Neuronpedia

    INDEX
    Explanations

    within, used, from, generate

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    內容
    0.57
    塢
    0.54
    内容
    0.51
    م
    0.49
     Survive
    0.46
    沒有
    0.46
     Workshops
    0.46
     buffs
    0.45
     rockers
    0.44
    蹌
    0.44
    POSITIVE LOGITS
    preferably
    0.47
    CurrentImageData
    0.46
     বোল
    0.46
     માન
    0.45
     خواهد
    0.44
    と思われる
    0.43
    idi
    0.43
     consideradas
    0.42
     जिंद
    0.42
    ти
    0.42
    Act Density 0.001%

    No Known Activations