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

    Neuronpedia

    INDEX
    Explanations

    terms related to governance and legal frameworks

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

    followed by punctuation or related to writing

    np_acts-logits-general · gemini-2.0-flash

    specific nouns and concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     vôtre
    -0.79
     ferons
    -0.63
     acaso
    -0.61
    Географи
    -0.57
     espirituales
    -0.57
     mattino
    -0.57
     pioggia
    -0.55
     mensuales
    -0.55
     nôtre
    -0.54
     suyo
    -0.54
    POSITIVE LOGITS
     Wikimedijinoj
    0.85
    .";
    0.74
     "]";
    0.73
    %");
    0.73
    .");
    0.72
    -,
    0.71
    "){
    0.71
    ")){
    0.69
    Hentet
    0.69
    }),
    0.68
    Act Density 1.976%

    No Known Activations