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

    Neuronpedia

    INDEX
    Explanations

    conversational korean question endings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    【
    0.83
    すべての
    0.80
    その
    0.79
    〔
    0.79
    あるいは
    0.77
    ――
    0.76
    걔
    0.72
    または
    0.72
    正しい
    0.71
    特定の
    0.70
    POSITIVE LOGITS
     소개해
    0.98
    했어요
    0.89
     ㅎㅎ
    0.89
    ~
    0.88
     Vocês
    0.87
     Œ
    0.85
    ~~
    0.83
    ~!
    0.83
     사진
    0.76
    께
    0.76
    Act Density 0.009%

    No Known Activations