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

    Neuronpedia

    INDEX
    Explanations

    instances of code syntax and structure

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

    code keywords and identifiers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     يتيمه
    -0.61
    IsContent
    -0.60
     незавершена
    -0.60
     ModelExpression
    -0.57
    httphttps
    -0.56
     nonUne
    -0.54
     noDo
    -0.52
    TagMode
    -0.51
    sizeCache
    -0.51
    eqn
    -0.49
    POSITIVE LOGITS
    ChildScrollView
    0.87
    NgModule
    0.70
    setVerticalGroup
    0.59
     NgModule
    0.59
    viewDidLoad
    0.57
    FormTagHelper
    0.56
    __":
    0.56
    stateProvider
    0.53
    DoubleQuotes
    0.52
    __':
    0.52
    Act Density 0.002%

    No Known Activations