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

    Neuronpedia

    INDEX
    Explanations

    structure and organization in written text, particularly in academic or formal contexts

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

    Introductory or preliminary content

    np_acts-logits-general · gemini-2.0-flash

    first sections introduce topics

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    addContainerGap
    -0.69
     CreateTagHelper
    -0.61
    migrationBuilder
    -0.59
     póź
    -0.59
     uiteindelijk
    -0.59
    出版年
    -0.58
     posteriores
    -0.57
     afterwards
    -0.56
    jalá
    -0.55
     TAMBÉM
    -0.55
    POSITIVE LOGITS
     introductory
    1.16
    Preliminaries
    1.14
     introduction
    1.13
     Introduction
    1.12
     prelimin
    1.12
     preliminary
    1.07
     introductions
    1.07
    Introduction
    1.04
     preparatory
    0.98
     pre
    0.98
    Act Density 0.604%

    No Known Activations