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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "Introduction" and its variations in the text

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

    introduction section headings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ementara
    -0.66
    DEPORTES
    -0.65
    Cyfarwyddwr
    -0.63
    ſelben
    -0.61
    <unused42>
    -0.61
    <unused41>
    -0.61
    <unused20>
    -0.61
    <unused14>
    -0.61
    <unused3>
    -0.61
    [@BOS@]
    -0.61
    POSITIVE LOGITS
    INTRODUCTION
    0.36
    toObject
    0.33
     AppCompatTheme
    0.30
    Introduction
    0.28
    iornamento
    0.28
     introduction
    0.28
    HomeComponent
    0.28
    styleUrls
    0.27
     INTRODUCTION
    0.27
    RODUCTION
    0.26
    Act Density 0.024%

    No Known Activations