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

    Neuronpedia

    INDEX
    Explanations

    Reuters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     DFT
    0.42
     impure
    0.42
     uniquely
    0.42
     único
    0.42
     achieving
    0.41
     transforming
    0.40
     SaaS
    0.40
     HDPE
    0.40
     diferente
    0.40
     DirectX
    0.39
    POSITIVE LOGITS
    newspaper
    0.69
     newspaper
    0.68
    journalist
    0.67
     magazine
    0.63
     Magazine
    0.63
    magazine
    0.62
     journalist
    0.59
    news
    0.57
     periodista
    0.57
     periodistas
    0.57
    Act Density 0.003%

    No Known Activations