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

    Neuronpedia

    INDEX
    Explanations

    definitions of classes in various programming languages

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

    Code-related keywords: class, struct

    np_acts-logits-general · gemini-2.0-flash

    class and struct code definitions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     again
    -0.40
     nuevamente
    -0.39
     tampoco
    -0.38
     vedno
    -0.38
     Ceramby
    -0.38
     isNameExpr
    -0.37
     podamos
    -0.37
    RouterModule
    -0.35
     lagi
    -0.35
    again
    -0.35
    POSITIVE LOGITS
    setVerticalGroup
    0.93
     astore
    0.75
    Hochspringen
    0.72
     AssemblyTitle
    0.72
    CreateModel
    0.69
    class
    0.68
    Parcelize
    0.65
    dataclass
    0.65
     class
    0.64
    hdashline
    0.62
    Act Density 0.036%

    No Known Activations