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

    Neuronpedia

    INDEX
    Explanations

    discussion of political norms and the behavior of political figures

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

    before adverbs/adjectives

    np_acts-logits-general · gemini-2.0-flash

    is governed or is important

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     eseguire
    -0.62
     Erişim
    -0.62
     Процитовано
    -0.59
    consulté
    -0.58
    umented
    -0.56
     consecutively
    -0.55
     prouve
    -0.55
     przeznac
    -0.55
     Angaben
    -0.54
     lèvres
    -0.54
    POSITIVE LOGITS
     plau
    0.70
    <_>
    0.69
     EINVAL
    0.64
    umbra
    0.62
     ")");
    0.61
    =[];
    0.58
    ejercicio
    0.57
     jedenfalls
    0.57
     broadly
    0.56
    colage
    0.56
    Act Density 1.194%

    No Known Activations