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

    Neuronpedia

    INDEX
    Explanations

    bring paste

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    我们在
    0.52
    如果我们
    0.52
    我们要
    0.52
     hicimos
    0.48
     fizemos
    0.46
    我們要
    0.45
    हमने
    0.44
    楽しめる
    0.43
    ชีพ
    0.42
    ที่เรา
    0.42
    POSITIVE LOGITS
    Bring
    0.82
     Bring
    0.82
     paste
    0.80
    Paste
    0.78
     Paste
    0.77
    bring
    0.72
     bring
    0.70
    paste
    0.69
     pasting
    0.68
     Please
    0.65
    Act Density 0.099%

    No Known Activations