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

    Neuronpedia

    INDEX
    Explanations

    quality

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     coll
    -0.08
     कि
    -0.08
     wijzen
    -0.07
    λωση
    -0.07
     Berd
    -0.07
    FXML
    -0.07
     incluso
    -0.07
     મુક
    -0.07
     Mengen
    -0.07
     buddy
    -0.07
    POSITIVE LOGITS
     assurance
    0.09
     workmanship
    0.09
     Assurance
    0.09
     العالية
    0.09
    空气
    0.08
     عالية
    0.08
     sonore
    0.08
    vr
    0.08
    cə
    0.08
    -quality
    0.08
    Act Density 0.031%

    No Known Activations