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

    Neuronpedia

    INDEX
    Explanations

    jar files and libraries

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    データ
    0.44
    ಾನ
    0.41
    默认
    0.40
     데이터
    0.38
    يمق
    0.37
     데이터를
    0.36
     fdata
    0.36
     Catt
    0.36
    ঞ্চি
    0.35
     getData
    0.35
    POSITIVE LOGITS
     jar
    0.92
    jar
    0.90
    JAR
    0.88
     JAR
    0.87
     jars
    0.86
    jars
    0.80
    Jar
    0.80
     Jar
    0.77
     lib
    0.62
    libs
    0.61
    Act Density 0.003%

    No Known Activations