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

    Neuronpedia

    INDEX
    Explanations

    moral character, follows this, use modern, which won

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    o
    0.91
    ுள்ளார்
    0.90
     holen
    0.80
    ла
    0.79
    ר
    0.79
    ㌔
    0.77
    ἐ
    0.76
    рг
    0.75
     הייתה
    0.75
    ுள்ளனர்
    0.74
    POSITIVE LOGITS
     TreeNode
    0.86
    ğı
    0.82
     Reigns
    0.79
    作为一个
    0.78
    تی
    0.74
     Qxa
    0.73
    较为
    0.71
     confusion
    0.70
    腆
    0.70
    旁边
    0.70
    Act Density 0.000%

    No Known Activations