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

    Neuronpedia

    INDEX
    Explanations

    proper nouns and names related to significant political figures and organizations, particularly in an American context

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

    Names of political figures

    np_acts-logits-general · gemini-2.0-flash

    US presidents and politicians

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    addGap
    -0.76
    WEBPACK
    -0.61
    يكب
    -0.60
    arnes
    -0.52
     برانيه
    -0.51
    只见
    -0.50
     է
    -0.50
     متعلقه
    -0.50
    "> 
    -0.50
    (.*
    -0.50
    POSITIVE LOGITS
     certainly
    1.25
    certainly
    1.09
     clearly
    1.01
     Certainly
    0.98
     obviously
    0.95
     probably
    0.95
    Clearly
    0.94
     surely
    0.94
    Certainly
    0.94
     undoubtedly
    0.92
    Act Density 0.651%

    No Known Activations