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

    Neuronpedia

    INDEX
    Explanations

    terms and phrases related to legal or governmental functions and roles

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

    German words or phrases

    np_acts-logits-general · gemini-2.0-flash

    legal and administrative positions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Javan
    -0.82
     Aene
    -0.67
     conqueror
    -0.67
     Tratado
    -0.65
     Etrus
    -0.65
     Bélgica
    -0.64
     Fortaleza
    -0.62
     Phoen
    -0.62
     Swedes
    -0.61
     Pozn
    -0.61
    POSITIVE LOGITS
     CreateTagHelper
    0.72
    secret
    0.62
     deleg
    0.58
    Secret
    0.56
     Secret
    0.52
     secret
    0.52
    Dire
    0.51
     SECRET
    0.50
     Dire
    0.50
    SECRET
    0.49
    Act Density 0.046%

    No Known Activations