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

    Neuronpedia

    INDEX
    Explanations

    expressions of humor, particularly those related to joking or sarcasm

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

    not serious

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     geïsole
    -0.38
     farba
    -0.38
     Quinn
    -0.37
    енча
    -0.37
     Witkin
    -0.36
     useRouter
    -0.36
     trụ
    -0.36
    waitFor
    -0.35
     voort
    -0.35
     razões
    -0.33
    POSITIVE LOGITS
     propOrder
    0.68
     ویکی‌پدیا
    0.61
    Personendaten
    0.59
    ->___
    0.55
    aarrggbb
    0.54
    Vidite
    0.54
     يتيمه
    0.54
     disambiguazione
    0.53
     Exacts
    0.50
    Jeografia
    0.49
    Act Density 0.009%

    No Known Activations