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

    Neuronpedia

    INDEX
    Explanations

    code structure and syntax elements in programming

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

    initialization

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     autorytatywna
    -0.74
    autorest
    -0.73
     ObjectParameter
    -0.71
    featureID
    -0.65
    errHandler
    -0.65
     resourceCulture
    -0.63
    verwijspagina
    -0.59
     nahilalakip
    -0.57
    ImageContext
    -0.57
     pinulongan
    -0.56
    POSITIVE LOGITS
     early
    0.54
     initial
    0.50
    PostConstruct
    0.50
     awal
    0.48
     초기
    0.46
    early
    0.46
     inicial
    0.46
     iniciales
    0.46
    Initial
    0.45
     Initial
    0.45
    Act Density 0.006%

    No Known Activations