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

    Neuronpedia

    INDEX
    Explanations

    specific structural elements and markup within a document or code

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

    world to everywhere

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    請繼續往下閱讀
    -0.50
    NameInMap
    -0.44
    roek
    -0.43
    projection
    -0.40
    __*/
    -0.39
    pdo
    -0.37
    Incoming
    -0.37
    
    -0.37
    iál
    -0.37
    ỡng
    -0.37
    POSITIVE LOGITS
     everywhere
    0.78
     überall
    0.68
    各地
    0.67
    everywhere
    0.65
     Everywhere
    0.65
     nationwide
    0.63
     везде
    0.62
     partout
    0.61
     worldwide
    0.60
    Everywhere
    0.57
    Act Density 0.172%

    No Known Activations