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

    Neuronpedia

    INDEX
    Explanations

    only or unique instances

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    整体
    0.80
    濆
    0.80
    használ
    0.77
     blanchâtre
    0.74
     Arduino
    0.74
    整體
    0.73
     cortos
    0.72
    idł
    0.72
     arduino
    0.72
    的数据
    0.71
    POSITIVE LOGITS
    唯一
    2.54
     единственный
    2.47
     एकमात्र
    2.35
    唯一的
    2.23
     един
    2.13
     única
    1.90
     الوح
    1.90
     একমাত্র
    1.87
     únicas
    1.82
     eneste
    1.81
    Act Density 0.087%

    No Known Activations