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

    Neuronpedia

    INDEX
    Explanations

    list of options

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    䣼
    0.51
    ロール
    0.46
    反应
    0.45
     تمر
    0.45
     sản
    0.44
    坐
    0.41
    数组
    0.40
    ships
    0.40
    一番
    0.39
     تناول
    0.39
    POSITIVE LOGITS
     Hj
    0.52
    ఞ
    0.48
     Egi
    0.46
     Shahid
    0.46
     unas
    0.45
    ar
    0.45
     *,
    0.45
     Augmented
    0.44
     prie
    0.43
     augmented
    0.43
    Act Density 0.003%

    No Known Activations