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

    Neuronpedia

    INDEX
    Explanations

    the presence of the article "a" and phrases describing personal attributes or identities

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

    "a" followed by a word

    np_acts-logits-general · gemini-2.0-flash

    a before descriptions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     rekke
    -0.48
    这位
    -0.47
    astrous
    -0.46
    谁能
    -0.46
    他对
    -0.45
     様
    -0.44
    thalt
    -0.43
    着
    -0.43
    ıcı
    -0.43
    -0.43
    POSITIVE LOGITS
    Datuak
    0.74
    WARE
    0.73
     BorderRadius
    0.71
    دانشنامهٔ
    0.70
    IsContent
    0.69
     JpaRepository
    0.69
     ویکی‌پدیا
    0.68
    AddTagHelper
    0.66
    fraid
    0.66
     الحره
    0.65
    Act Density 0.160%

    No Known Activations