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

    Neuronpedia

    INDEX
    Explanations

    deal with

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     וכ
    1.95
    ні
    1.72
     l
    1.67
    п
    1.66
     کام
    1.63
    కె
    1.63
    ς
    1.63
    ко
    1.61
    чні
    1.59
    ри
    1.58
    POSITIVE LOGITS
    मणि
    2.08
    ל
    2.05
     Ciò
    2.03
     Também
    2.02
    LEMN
    1.92
    ুমার
    1.92
    ن
    1.92
    okkal
    1.89
    脚注
    1.88
    ನನ್ನು
    1.87
    Act Density 0.143%

    No Known Activations