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

    Neuronpedia

    INDEX
    Explanations

    material composition and properties

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Viitteet
    -0.94
    étro
    -0.83
    jaard
    -0.82
    тивні
    -0.81
    笥
    -0.80
    　　《
    -0.80
    ึ้น
    -0.80
     продукта
    -0.77
    水果
    -0.75
    ksyon
    -0.75
    POSITIVE LOGITS
     material
    1.12
     materiaal
    0.91
     choice
    0.89
     composition
    0.89
     exterior
    0.89
     Material
    0.87
    material
    0.83
    exterior
    0.82
    composition
    0.81
     principale
    0.81
    Act Density 0.004%

    No Known Activations