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

    Neuronpedia

    INDEX
    Explanations

    negative consequences or risks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     budding
    1.07
     pomp
    1.03
    óle
    1.00
     competente
    0.99
     округа
    0.98
     বস্ত
    0.95
    ropic
    0.95
     dado
    0.94
    良好的
    0.93
     prawidł
    0.93
    POSITIVE LOGITS
     яких
    1.37
    ни
    1.30
     Implications
    1.20
    ित
    1.15
     写真
    1.15
    ेश
    1.14
     Priscilla
    1.11
    RDD
    1.11
     Всего
    1.11
    ла
    1.10
    Act Density 0.000%

    No Known Activations