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

    Neuronpedia

    INDEX
    Explanations

    law enforcement

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    .
    1.67
    '
    1.59
    ’
    1.45
    ır
    1.17
    ة
    1.17
    ना
    1.16
    У
    1.13
    يم
    1.13
    áról
    1.12
    एक
    1.10
    POSITIVE LOGITS
     in
    1.54
     were
    1.44
     to
    1.43
     on
    1.41
    to
    1.38
    malign
    1.38
     aren
    1.37
     imprisoned
    1.31
     hectares
    1.30
     all
    1.29
    Act Density 0.188%

    No Known Activations