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

    Neuronpedia

    INDEX
    Explanations

    code coverage

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    aughton
    0.46
    sections
    0.43
     covered
    0.42
    蘊
    0.41
     weakness
    0.40
    やす
    0.39
     weaknesses
    0.38
     جرم
    0.38
     touched
    0.38
     panas
    0.37
    POSITIVE LOGITS
    Istanbul
    0.47
     проверить
    0.46
     clover
    0.44
     verificare
    0.43
    保険
    0.43
    istanbul
    0.43
     测试
    0.42
    jacoco
    0.42
     Co
    0.42
     Clover
    0.42
    Act Density 0.002%

    No Known Activations