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

    Neuronpedia

    INDEX
    Explanations

    programming-related structures, particularly class definitions and their characteristics in code

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

    programming class definitions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     مشين
    -0.48
    -0.47
    ंदीखरीदारी
    -0.47
    AsUp
    -0.44
    TypedDataSet
    -0.42
    UserScript
    -0.42
     betweenstory
    -0.41
    InputTagHelper
    -0.41
    NameInMap
    -0.40
    SerializedSize
    -0.40
    POSITIVE LOGITS
     getClass
    0.59
     isKindOfClass
    0.54
    Parcelize
    0.54
     class
    0.54
     Class
    0.54
     NgModule
    0.54
    endmodule
    0.52
    classes
    0.51
    class
    0.51
    getClass
    0.51
    Act Density 0.308%

    No Known Activations