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

    Neuronpedia

    INDEX
    Explanations

    references to royal entities or figures

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

    royal and related contexts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     gebra
    -0.37
    App
    -0.34
     use
    -0.34
     Abraham
    -0.34
    ような
    -0.34
     складу
    -0.33
     September
    -0.33
    DDT
    -0.33
     new
    -0.32
     E
    -0.32
    POSITIVE LOGITS
     royal
    1.55
    royal
    1.30
     royals
    1.05
     royalty
    0.98
     ROYAL
    0.98
     könig
    0.94
     royale
    0.91
     Royals
    0.88
    Royal
    0.84
     roy
    0.81
    Act Density 0.008%

    No Known Activations