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

    Neuronpedia

    INDEX
    Explanations

    wikipedia links

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    -
    0.77
    s
    0.76
    7
    0.75
    8
    0.73
    ing
    0.73
    am
    0.71
    ah
    0.71
    9
    0.69
    he
    0.65
    ce
    0.63
    POSITIVE LOGITS
    ল
    0.62
     mês
    0.61
    差不多
    0.59
     இந்திய
    0.58
     стаўкі
    0.57
    维度
    0.57
     performers
    0.57
     вершины
    0.57
    眼镜
    0.56
    代谢
    0.56
    Act Density 0.012%

    No Known Activations