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

    Neuronpedia

    INDEX
    Explanations

    programming constructs related to classes and their properties in a codebase

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Keywords preceding Kotlin or Java code

    np_acts-logits-general · gemini-2.0-flash

    programming keywords

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    rungsseite
    -0.85
     gynhyrchwyd
    -0.80
     pinulongan
    -0.79
    хьтан
    -0.77
    Билгалдахарш
    -0.77
    WriteBarrier
    -0.72
    Παραπομπές
    -0.69
     CreateTagHelper
    -0.67
    PYX
    -0.66
    Хьажоргаш
    -0.66
    POSITIVE LOGITS
     val
    0.90
    val
    0.86
     fun
    0.85
    fun
    0.76
    VAL
    0.55
    lateinit
    0.50
     FUN
    0.49
    Val
    0.49
    Fun
    0.47
    FUN
    0.46
    Act Density 0.063%

    No Known Activations