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

    Neuronpedia

    INDEX
    Explanations

    Spanish words and suffixes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ath
    0.51
    ATING
    0.51
      
    0.50
     ber
    0.48
     pr
    0.48
     seq
    0.47
    ALLY
    0.46
     ot
    0.45
     wer
    0.44
     자세
    0.44
    POSITIVE LOGITS
    椃
    1.00
    0.98
    ibilidad
    0.97
    ografía
    0.97
    imiento
    0.96
    resultados
    0.96
    ￳
    0.96
    ificación
    0.95
    certificado
    0.94
    iciencia
    0.93
    Act Density 0.249%

    No Known Activations