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

    Neuronpedia

    INDEX
    Explanations

    Kotlin, Android, Swift development

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ():
    0.40
    :");
    0.40
     фор
    0.38
     submodule
    0.37
     beforeDir
    0.37
    TERM
    0.37
    ពិ
    0.36
    리지
    0.36
    턴
    0.36
    ɪ
    0.36
    POSITIVE LOGITS
    android
    0.61
     Android
    0.56
    Android
    0.56
    swift
    0.52
     android
    0.50
     Kotlin
    0.48
     ofic
    0.48
     Андроид
    0.48
    代码
    0.46
     Swift
    0.45
    Act Density 0.002%

    No Known Activations