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

    Neuronpedia

    INDEX
    Explanations

    興味深い，元気，話題，参考

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     permas
    0.46
    聲
    0.43
    atsioon
    0.42
    ᄉ
    0.41
    }]}\
    0.41
    قيم
    0.40
     Audiodateien
    0.39
    ಝ
    0.39
    樂
    0.39
     "~/
    0.39
    POSITIVE LOGITS
     feeling
    0.50
    の一つ
    0.43
    feeling
    0.43
    だった
    0.43
     compelling
    0.42
    で
    0.42
     intent
    0.41
     представление
    0.41
    ルの
    0.40
     feel
    0.40
    Act Density 0.012%

    No Known Activations