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

    Neuronpedia

    INDEX
    Explanations

    articles, pronouns, and other function words used in sentences

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

    path separators or delimiters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    <unused28>
    -0.89
    <unused8>
    -0.89
    <unused41>
    -0.89
    <unused74>
    -0.89
    <unused43>
    -0.89
    <unused51>
    -0.88
    <unused79>
    -0.88
    <unused16>
    -0.88
    <unused3>
    -0.88
    <unused14>
    -0.88
    POSITIVE LOGITS
    <unused62>
    0.25
    جستارهای
    0.24
     nahilalakip
    0.24
     et
    0.23
    <unused60>
    0.23
     상세
    0.23
     textStatus
    0.23
    <unused61>
    0.22
    verwijspagina
    0.22
     and
    0.21
    Act Density 0.007%

    No Known Activations