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

    Neuronpedia

    INDEX
    Explanations

    closing code syntax

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    fireFlower
    0.45
     मूल्यों
    0.44
    надцать
    0.44
    ക്ഷേ
    0.44
    verticalLayout
    0.44
    ="("
    0.44
    xRt
    0.44
     कहें
    0.44
    »،
    0.43
    istisch
    0.43
    POSITIVE LOGITS
    );
    0.86
     )
    0.78
     );
    0.75
     '')
    0.74
    )
    0.74
    .)
    0.73
     [])
    0.68
     "");
    0.67
     "")
    0.66
    ).
    0.64
    Act Density 0.024%

    No Known Activations