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

    Neuronpedia

    INDEX
    Explanations

    roleplay greetings and introductions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     hereof
    0.87
    下图
    0.75
     herewith
    0.75
    〆
    0.74
    Another
    0.74
    Berikut
    0.73
     ongoing
    0.73
    यहां
    0.71
    Этот
    0.71
    Here
    0.69
    POSITIVE LOGITS
    assie
    0.81
     আমাকে
    0.75
     jolly
    0.74
    姨
    0.73
     happily
    0.72
     »
    0.71
     내가
    0.71
    asso
    0.70
     আ
    0.69
    াদে
    0.69
    Act Density 0.087%

    No Known Activations