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

    Neuronpedia

    INDEX
    Explanations

    sections of a document related to introducing topics and headings

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

    introduction section header

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     незавершена
    -0.92
     فريبيس
    -0.86
    ImageContext
    -0.82
    MethodManager
    -0.78
     pinulongan
    -0.78
    RTLR
    -0.77
    SBATCH
    -0.77
     queſta
    -0.77
     للمعارف
    -0.76
     Paglinawan
    -0.74
    POSITIVE LOGITS
    Introduction
    0.79
    INTRODUCTION
    0.78
     INTRODUCTION
    0.68
     Introduction
    0.66
     introduction
    0.60
    introduction
    0.55
    Intro
    0.45
    INTRODUCCIÓN
    0.41
    Introdu
    0.41
    RODUCTION
    0.41
    Act Density 0.002%

    No Known Activations