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

    Neuronpedia

    INDEX
    Explanations

    instances of object creation or initialization in code snippets

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

    create and new

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     betweenstory
    -0.76
     BrowserModule
    -0.64
     kysy
    -0.56
     OMITBAD
    -0.55
    //
    -0.55
    /**
    -0.50
    lapsingToolbar
    -0.49
     HomeController
    -0.48
    CompilerServices
    -0.48
     ainfi
    -0.47
    POSITIVE LOGITS
    create
    0.63
     clone
    0.56
    createElement
    0.55
     create
    0.54
    clone
    0.50
     dummy
    0.50
     customized
    0.49
     simple
    0.48
     standard
    0.48
     natural
    0.47
    Act Density 0.012%

    No Known Activations