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

    Neuronpedia

    INDEX
    Explanations

    references to high-ranking individuals or officials in various contexts

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

    high rank officials

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    astify
    -0.45
     variation
    -0.40
    ReusableCell
    -0.38
     sensação
    -0.38
     بيها
    -0.36
    entador
    -0.36
     tempio
    -0.36
    úsqueda
    -0.35
     cycle
    -0.35
     messy
    -0.35
    POSITIVE LOGITS
     executives
    0.62
    Autoritní
    0.62
     officials
    0.61
     صوتيه
    0.59
     pimpinan
    0.57
     statesmen
    0.56
    RectangleBorder
    0.53
     nakalista
    0.52
    Executives
    0.51
     vezet
    0.51
    Act Density 0.026%

    No Known Activations