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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating dedication or focus on a particular subject or theme

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

    introduces or describes subjects

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     للمعارف
    -0.76
     autorytatywna
    -0.71
     kasarigan
    -0.69
     Biôgrafia
    -0.68
     ویکی‌پدیا
    -0.64
    KommentareTeilen
    -0.64
     nonatomic
    -0.63
     CURIAM
    -0.62
    rungsseite
    -0.61
    RenderAtEndOf
    -0.61
    POSITIVE LOGITS
     concept
    0.41
     sub
    0.40
     inspired
    0.38
     art
    0.37
     We
    0.37
     time
    0.37
     design
    0.36
     
    0.35
    se
    0.35
     aim
    0.35
    Act Density 0.008%

    No Known Activations