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

    Neuronpedia

    INDEX
    Explanations

    action verbs indicating significant activities or results in various contexts

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

    presenting or describing methods

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     football
    -0.38
     Porém
    -0.37
     Sherwood
    -0.37
     tromper
    -0.36
    níky
    -0.36
     réserver
    -0.36
     giorn
    -0.36
     fundación
    -0.35
    tlement
    -0.35
     bleue
    -0.34
    POSITIVE LOGITS
    IntoConstraints
    0.59
     StatelessWidget
    0.51
     незавершена
    0.50
    脚注の使い方
    0.50
     nakalista
    0.48
     ویکی‌پدیا
    0.48
     snippetHide
    0.48
    KommentareTeilen
    0.47
    DockStyle
    0.47
    Rujuakan
    0.46
    Act Density 0.359%

    No Known Activations