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

    Neuronpedia

    INDEX
    Explanations

    decorative and classic elements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     distrust
    0.71
     repudi
    0.68
     jurisprudence
    0.68
     epistem
    0.67
     mistrust
    0.64
     dehuman
    0.63
     inescap
    0.63
    criminal
    0.62
     virulent
    0.61
    推定
    0.61
    POSITIVE LOGITS
    可以选择
    0.80
     decorative
    0.80
     Classic
    0.79
     можно
    0.78
     Decor
    0.77
     decorar
    0.77
     можна
    0.75
     Decorative
    0.74
     classic
    0.73
     décoration
    0.73
    Act Density 0.099%

    No Known Activations