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

    Neuronpedia

    INDEX
    Explanations

    proper nouns, especially names related to individuals involved in legal or judicial contexts

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

    given names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     seyn
    -0.45
    ActionCreators
    -0.45
     NSCoder
    -0.43
    原始内容存档
    -0.41
    odyear
    -0.41
    assertEqual
    -0.41
     BoxFit
    -0.40
    ThroughAttribute
    -0.40
    LikeLiked
    -0.39
    tgz
    -0.38
    POSITIVE LOGITS
     Courtney
    1.24
    Courtney
    1.14
     Clarence
    0.84
    Clarence
    0.77
     Dominique
    0.77
     Valerie
    0.76
    Valerie
    0.69
    Dominique
    0.68
     Terence
    0.65
     Terrence
    0.62
    Act Density 0.002%

    No Known Activations