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

    Neuronpedia

    INDEX
    Explanations

    Habilidad, precious

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     UK
    0.15
    essional
    0.15
    +
    0.14
     Кі
    0.14
     CR
    0.13
     classy
    0.13
     hefty
    0.13
     lycée
    0.13
    7
    0.13
     layup
    0.13
    POSITIVE LOGITS
     administrador
    0.17
     objetivo
    0.16
    鳎
    0.16
    اید
    0.15
     necesidad
    0.15
     εί
    0.14
     añad
    0.14
     आवश्यकता
    0.14
     posible
    0.14
     último
    0.14
    Act Density 1.481%

    No Known Activations