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

    Neuronpedia

    INDEX
    Explanations

    quantity, number, resource, quarter

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     gerar
    0.89
     permitir
    0.89
     ders
    0.84
     kontrol
    0.81
     gera
    0.81
     pós
    0.80
     komplex
    0.79
    et
    0.78
     sozial
    0.76
     berd
    0.76
    POSITIVE LOGITS
    荏
    0.79
    march
    0.77
    疾病
    0.75
    清
    0.74
    电影
    0.73
     μία
    0.73
    精华
    0.71
    vx
    0.71
    ીએ
    0.71
    iciembre
    0.70
    Act Density 0.000%

    No Known Activations