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

    Neuronpedia

    INDEX
    Explanations

    from the other

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    <0x80>
    1.13
    ার
    1.10
    sentences
    1.03
     faptul
    0.99
     其中
    0.99
     různ
    0.98
    UFACT
    0.97
    Danh
    0.97
     isLoading
    0.96
    其中
    0.95
    POSITIVE LOGITS
     creer
    1.00
    ті
    0.97
     Worse
    0.97
    ie
    0.93
    నా
    0.93
     zosta
    0.91
    𝐢
    0.88
    ல்
    0.87
    ن
    0.87
    ார்
    0.87
    Act Density 0.136%

    No Known Activations