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

    Neuronpedia

    INDEX
    Explanations

    HTML tag elements

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

    multilingual text and code snippets

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     betweenstory
    -0.48
    yarnpkg
    -0.45
    APPLAUSE
    -0.41
    ("}\
    -0.38
    phosa
    -0.37
    thâu
    -0.36
    braio
    -0.36
    transQ
    -0.36
    Zusammenfassung
    -0.36
    DOCTYPE
    -0.35
    POSITIVE LOGITS
    はじめに
    0.50
    الحياه
    0.49
     ब्रेकडाउन
    0.47
    KommentareTeilen
    0.47
    __*/
    0.46
     Exacts
    0.45
     beginnetje
    0.45
    StoryboardSegue
    0.45
    awtextra
    0.43
    uxxxx
    0.42
    Act Density 0.005%

    No Known Activations