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

    Neuronpedia

    INDEX
    Explanations

    a gentle, smaller

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ),
    1.07
     fondly
    1.03
     aujourd
    1.01
    :
    0.98
    ,
    0.96
     passionately
    0.96
     immigrants
    0.94
     kics
    0.94
     població
    0.93
     wanting
    0.93
    POSITIVE LOGITS
     специальных
    1.24
    3
    1.13
    AR
    1.09
    Про
    1.07
    Ти
    1.03
    Стра
    1.03
    4
    1.03
    Тре
    1.02
    MLB
    1.02
     методов
    1.00
    Act Density 1.088%

    No Known Activations