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

    Neuronpedia

    INDEX
    Explanations

    code and programming contexts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     mele
    0.72
     ойно
    0.71
     सुनील
    0.71
    mują
    0.68
     Dari
    0.67
    Pierre
    0.66
    Marcel
    0.66
    💊
    0.66
    menopausal
    0.66
     intertw
    0.65
    POSITIVE LOGITS
    पोस्ट
    0.59
     დაბ
    0.58
    搜索引擎
    0.56
    Cream
    0.56
    壹
    0.56
    ্জ
    0.56
    ހ
    0.55
     موقف
    0.55
    """
    0.55
     ceil
    0.54
    Act Density 0.027%

    No Known Activations