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

    Neuronpedia

    INDEX
    Explanations

    return value assignments

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    .)
    0.59
    );
    0.54
    .);
    0.54
    ).
    0.48
    .).
    0.48
    .),
    0.46
    .):
    0.45
    ?).
    0.45
     considérons
    0.45
    !).
    0.44
    POSITIVE LOGITS
     \
    0.62
     kwargs
    0.46
    <0x80>
    0.43
     estudos
    0.43
    ‪‬
    0.43
     monographs
    0.42
     රස
    0.42
     studies
    0.41
    ции
    0.41
    kwargs
    0.40
    Act Density 0.074%

    No Known Activations