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

    Neuronpedia

    INDEX
    Explanations

    security model

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     имели
    0.32
     있었다
    0.30
    ക്കേണ്ട
    0.30
    Perhaps
    0.29
     perhaps
    0.28
     있었
    0.28
     pecuniary
    0.28
    之事
    0.27
     monomial
    0.27
    URER
    0.27
    POSITIVE LOGITS
     sẽ
    0.34
     soggy
    0.32
     súper
    0.29
     ótima
    0.29
     így
    0.28
     dễ
    0.28
    í
    0.28
     sensação
    0.27
     takže
    0.27
     સારું
    0.27
    Act Density 0.004%

    No Known Activations