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

    Neuronpedia

    INDEX
    Explanations

    the keyword "new" indicating the creation of new instances or objects in code

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

    object instantiation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ſelf
    -0.48
    -0.47
    GEBURTSDATUM
    -0.44
     ſtate
    -0.42
    )_/¯
    -0.42
     $_"
    -0.42
     Italijani
    -0.41
    }{*}{}
    -0.41
     }</
    -0.38
     itſelf
    -0.38
    POSITIVE LOGITS
     new
    1.17
    new
    0.82
     CreateTagHelper
    0.72
     AssemblyTitle
    0.67
    ValueStyle
    0.65
     neue
    0.65
     nieuwe
    0.65
     AssemblyCulture
    0.64
     nuovi
    0.64
     novas
    0.63
    Act Density 0.003%

    No Known Activations