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

    Neuronpedia

    INDEX
    Explanations

    it looks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    지털
    0.52
    والفقار
    0.50
     politiche
    0.47
     avrebbe
    0.46
     debía
    0.46
     Luật
    0.44
    逻辑
    0.44
    Stride
    0.43
    varchar
    0.43
     допуска
    0.43
    POSITIVE LOGITS
    底部
    0.52
     /
    0.46
    也是
    0.42
     NASA
    0.41
     USA
    0.40
     Ingredients
    0.40
    另
    0.40
     ACTUAL
    0.39
     bottom
    0.39
     αξ
    0.39
    Act Density 0.013%

    No Known Activations