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

    Neuronpedia

    INDEX
    Explanations

    Java programming language constructs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     carcinomas
    0.58
     maxillary
    0.56
     compds
    0.52
     macroscopic
    0.52
     lowland
    0.52
     terres
    0.51
     mastic
    0.50
     compd
    0.50
     sediments
    0.50
     Exptl
    0.50
    POSITIVE LOGITS
    java
    0.72
     LocalDate
    0.71
    Java
    0.71
    Kotlin
    0.67
    pojo
    0.66
    netty
    0.66
    LocalDateTime
    0.65
     JDK
    0.65
    鍗
    0.65
     LocalDateTime
    0.64
    Act Density 0.080%

    No Known Activations