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

    Neuronpedia

    INDEX
    Explanations

    key phrases related to political disputes and conflicts

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

    Follows "the", or a quotation mark

    np_acts-logits-general · gemini-2.0-flash

    titles or specific identifiers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     kasarigan
    -0.58
     виправивши
    -0.56
    ]?.
    -0.54
    ViewFeatures
    -0.52
    一出
    -0.51
    huriyet
    -0.49
    stuffs
    -0.48
    |]
    -0.48
     fich
    -0.46
    llery
    -0.46
    POSITIVE LOGITS
     President
    1.47
     president
    1.40
    President
    1.26
     boss
    1.23
     PRESIDENT
    1.19
     Governor
    1.16
    president
    1.14
     governor
    1.14
    PRESIDENT
    1.06
     Minister
    1.05
    Act Density 0.317%

    No Known Activations