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

    Neuronpedia

    INDEX
    Explanations

    emojis and special characters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    та
    2.53
    ים
    2.47
    ت
    2.25
     वालों
    2.11
    ación
    2.08
    ↵
    2.05
    ot
    2.05
    ين
    1.98
    дцать
    1.95
    ข้อง
    1.92
    POSITIVE LOGITS
    ﺎ
    2.06
    ДЕ
    1.88
    llama
    1.84
     pubb
    1.82
    desde
    1.80
    cos
    1.77
    resTmp
    1.77
    kinase
    1.77
    Вели
    1.75
    െയ്
    1.75
    Act Density 0.123%

    No Known Activations