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

    Neuronpedia

    INDEX
    Explanations

    code structure and definitions in programming documentation

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

    code snippets and technical terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     パンチラ
    -0.88
    expandindo
    -0.88
    <unused41>
    -0.86
    <unused23>
    -0.86
    <unused74>
    -0.86
    <unused51>
    -0.86
    <unused8>
    -0.86
    <unused79>
    -0.85
    <unused28>
    -0.85
    <unused14>
    -0.85
    POSITIVE LOGITS
     Sénat
    0.22
    …
    0.20
     it
    0.20
    ıştı
    0.19
     alıntı
    0.19
     mouseClicked
    0.18
     thats
    0.18
     honneur
    0.18
    นั้น
    0.18
    vänd
    0.17
    Act Density 0.023%

    No Known Activations