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

    Neuronpedia

    INDEX
    Explanations

    two items or concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    I
    1.05
    ב
    1.05
    டிய
    1.04
    It
    1.04
    bu
    1.01
    댁
    1.00
    Wonderful
    1.00
    nya
    0.98
    K
    0.97
    boo
    0.96
    POSITIVE LOGITS
    виль
    1.26
    ⅜
    1.14
    ствен
    1.11
     />,
    1.11
    রাষ্ট
    1.06
    <unused8>
    1.06
    goers
    1.06
    ídos
    1.05
    //{
    1.05
     brazilian
    1.04
    Act Density 0.001%

    No Known Activations