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

    Neuronpedia

    INDEX
    Explanations

    C# Unity code

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    र
    2.58
    ES
    2.17
    ў
    2.07
    ifying
    1.98
    ate
    1.96
    st
    1.95
    us
    1.93
    ت
    1.92
    कीय
    1.90
    𝑡
    1.86
    POSITIVE LOGITS
    اً
    2.44
     vẻ
    2.21
     reum
    1.97
     recorr
    1.96
    hamento
    1.94
    εται
    1.89
     Equals
    1.89
     jez
    1.88
    カイブ
    1.86
     শুধ
    1.86
    Act Density 0.001%

    No Known Activations