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

    Neuronpedia

    INDEX
    Explanations

    sx3

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    茭
    0.73
    自定义
    0.72
    몽
    0.72
    ຕາມ
    0.72
    旁边
    0.71
     considerato
    0.71
     previsto
    0.70
    Người
    0.70
    다
    0.70
     vivere
    0.69
    POSITIVE LOGITS
     Еўропы
    0.88
     Convert
    0.79
     Mus
    0.78
    tedir
    0.78
     Clair
    0.77
     an
    0.77
     Six
    0.76
     An
    0.76
     Ap
    0.76
     Syl
    0.76
    Act Density 0.001%

    No Known Activations