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

    Neuronpedia

    INDEX
    Explanations

    titles and ranks of nobility

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

    counts and noble titles

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ciudadana
    -0.45
     Jerusalén
    -0.42
     vocale
    -0.40
     popolare
    -0.39
     democrática
    -0.38
    chtigkeit
    -0.37
    Algérie
    -0.37
     sanitaria
    -0.37
     FetchType
    -0.36
     permanentes
    -0.36
    POSITIVE LOGITS
     Countess
    0.94
     Count
    0.91
     count
    0.87
     Earl
    0.80
    Earl
    0.78
    Count
    0.77
     COUNT
    0.77
     Marquis
    0.75
     marquis
    0.75
     comte
    0.74
    Act Density 0.036%

    No Known Activations