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

    Neuronpedia

    INDEX
    Explanations

    Doctor Who and of America

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    al
    1.27
    esai
    1.17
    asının
    1.12
    ας
    1.10
    ী
    1.09
    eses
    1.08
     descans
    1.06
    ادہ
    1.05
     змо
    1.05
    тр
    1.04
    POSITIVE LOGITS
     o
    1.30
    个
    1.25
    rical
    1.20
    ATION
    1.19
    एं
    1.18
    ज
    1.18
    たくさんの
    1.16
    しまう
    1.15
    ان
    1.14
    lichen
    1.14
    Act Density 0.003%

    No Known Activations