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

    Neuronpedia

    INDEX
    Explanations

    requests for actions and inquiries

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     very
    0.57
     muito
    0.54
     rất
    0.54
     sangat
    0.52
     дуже
    0.50
     bardzo
    0.49
     muy
    0.48
     begitu
    0.48
     khá
    0.47
     очень
    0.47
    POSITIVE LOGITS
    看看
    1.02
    看一下
    0.88
    一下
    0.79
    试试
    0.75
    后再
    0.65
     awhile
    0.64
    想想
    0.63
    来看看
    0.61
    再说
    0.59
    してみてください
    0.58
    Act Density 0.004%

    No Known Activations