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

    Neuronpedia

    INDEX
    Explanations

    phrases related to political events and notable figures

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

    Following the word "the" or its capitalized form

    np_acts-logits-general · gemini-2.0-flash

    specific named entities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     outros
    -0.65
     others
    -0.64
    others
    -0.63
     altri
    -0.63
    autres
    -0.62
    yntaxException
    -0.60
     otras
    -0.59
    >`;
    -0.58
     outras
    -0.58
    //};
    -0.57
    POSITIVE LOGITS
     prestigious
    0.91
     famous
    0.89
     infamous
    0.89
     notorious
    0.86
     recém
    0.83
    famous
    0.80
     renowned
    0.78
     famed
    0.76
     hugely
    0.76
     recientemente
    0.74
    Act Density 0.645%

    No Known Activations