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

    Neuronpedia

    INDEX
    Explanations

    mentions of specific names or titles, particularly related to individuals and locations

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

    Emir, Amir, Prince, nationalities, places

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    afternoon
    -0.41
    HasBeen
    -0.41
     kasarigan
    -0.41
    Jpa
    -0.40
    spe
    -0.39
     Barnes
    -0.39
    Potato
    -0.38
     Barna
    -0.38
    cabe
    -0.38
    Nen
    -0.37
    POSITIVE LOGITS
     Emir
    1.84
     emir
    1.62
    Emir
    1.23
     Amir
    1.20
    Amir
    1.07
    amir
    0.85
     امیر
    0.70
    herzog
    0.68
     emirates
    0.67
     الأمير
    0.62
    Act Density 0.001%

    No Known Activations