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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "introduction" and related variations in the text

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

    document introductions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    erà
    -0.37
     firebaseConfig
    -0.31
     healthier
    -0.31
     Calidad
    -0.30
    SaveChangesAsync
    -0.30
     sil
    -0.29
     lesz
    -0.29
    textcolor
    -0.29
    DispatchToProps
    -0.28
     sabiduría
    -0.28
    POSITIVE LOGITS
    Introduction
    1.00
     Introduction
    0.92
     introduction
    0.89
    introduction
    0.89
    INTRODUCTION
    0.81
     introductions
    0.79
    Введение
    0.77
     INTRODUCTION
    0.75
     introducción
    0.75
    Introducción
    0.72
    Act Density 0.010%

    No Known Activations