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

    Neuronpedia

    INDEX
    Explanations

    combining, forming, organizing, considering

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     kl
    0.62
     (
    0.61
     kor
    0.60
    ING
    0.58
     sk
    0.55
    0.55
    :
    0.55
    !
    0.55
      
    0.53
     &
    0.52
    POSITIVE LOGITS
    usuario
    1.34
    ografía
    1.26
    acción
    1.20
    nombre
    1.18
    resultados
    1.18
    Usuario
    1.16
    ología
    1.15
    grupo
    1.15
    productos
    1.15
    direccion
    1.13
    Act Density 0.317%

    No Known Activations