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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "the" and variations thereof, indicating a focus on definite articles in the text

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

    dates and names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     apsau
    -0.44
    EndGlobalSection
    -0.42
     Lainnya
    -0.42
    Notae
    -0.41
     mengan
    -0.39
     įva
    -0.39
     constantemente
    -0.39
     Вікіпе
    -0.39
     samtidig
    -0.39
     ständig
    -0.38
    POSITIVE LOGITS
    ArrowToggle
    0.46
    PMailer
    0.43
     coords
    0.43
    itinéraire
    0.41
     setId
    0.40
    #+#
    0.39
    ConstraintMaker
    0.39
    endphp
    0.39
    awaiter
    0.39
     logits
    0.38
    Act Density 0.008%

    No Known Activations