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

    Neuronpedia

    INDEX
    Explanations

    concepts related to sovereignty and authority

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

    sovereignty

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Milán
    -0.54
    Egypte
    -0.51
    Égypte
    -0.44
     Maladies
    -0.43
     Egipto
    -0.42
     Améli
    -0.41
     Pologne
    -0.41
    Ethylbenzene
    -0.41
    Marzo
    -0.41
     Cataluña
    -0.41
    POSITIVE LOGITS
    vereignty
    1.84
     sovereignty
    1.84
     sovereign
    1.48
    vereign
    1.40
     Sovereign
    1.35
     souverain
    1.09
     Souver
    1.08
     souver
    1.00
     sovere
    0.96
     sover
    0.91
    Act Density 0.007%

    No Known Activations