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

    Neuronpedia

    INDEX
    Explanations

    IntelliJ IDEA and JetBrains IDEs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     시작
    0.66
    일상
    0.66
     Pedersen
    0.65
    二次
    0.65
     начина
    0.64
     ovlád
    0.63
     കലാ
    0.63
     Dada
    0.63
    申請
    0.62
     Geburtstag
    0.61
    POSITIVE LOGITS
     IntelliJ
    1.39
     Belarusian
    1.37
     Kotlin
    1.26
     Belarus
    1.18
    Belarus
    1.18
    Kotlin
    1.14
    intellij
    1.12
    Gradle
    1.03
    ГУ
    1.03
     Kursk
    1.02
    Act Density 0.010%

    No Known Activations