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

    Neuronpedia

    INDEX
    Explanations

    closing parenthesis or expression end

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ﹙
    0.52
    _
    0.51
    4
    0.50
    =}
    0.48
    $.}
    0.47
    _=
    0.47
    Scaling
    0.46
    DAL
    0.45
     、,
    0.45
    ="))
    0.44
    POSITIVE LOGITS
    )|
    0.59
    )\
    0.57
    ):
    0.54
    ):=
    0.54
    )...
    0.52
    )~
    0.49
     ஐந்து
    0.48
    )…
    0.48
     fuori
    0.47
    इस
    0.47
    Act Density 0.072%

    No Known Activations