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

    Neuronpedia

    INDEX
    Explanations

    mayo and related phrases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    s
    2.09
    ों
    1.94
    ы
    1.87
    ের
    1.82
    اً
    1.80
    uje
    1.73
     самим
    1.72
     pequeños
    1.69
    ات
    1.67
     टुकड़े
    1.67
    POSITIVE LOGITS
    м
    2.70
    т
    2.45
    та
    2.20
    ك
    2.17
    ле
    2.13
    ت
    1.91
    ли
    1.84
    َ
    1.77
    то
    1.76
    ла
    1.74
    Act Density 0.001%

    No Known Activations