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

    Neuronpedia

    INDEX
    Explanations

    units of measurement

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     (
    0.56
    িসহ
    0.44
     (**
    0.44
    。（
    0.43
    （
    0.41
     （
    0.41
     этом
    0.41
    ！（
    0.40
     daraus
    0.40
    SuppressWarnings
    0.39
    POSITIVE LOGITS
    ),”
    0.68
    ),
    0.60
    ),"
    0.60
    )”
    0.59
    )،
    0.57
    )....
    0.55
    ).”
    0.53
    ),'
    0.53
    )…
    0.53
    )"
    0.53
    Act Density 0.015%

    No Known Activations