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

    Neuronpedia

    INDEX
    Explanations

    document metadata elements and structural components

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

    preceding or related to "date" or "author"

    np_acts-logits-general · gemini-2.0-flash

    date, author, title fields

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    <eos>
    -0.58
     '
    -0.55
     meant
    -0.52
     
    -0.52
     and
    -0.50
     `
    -0.49
     at
    -0.48
     a
    -0.48
    |
    -0.47
    polizei
    -0.47
    POSITIVE LOGITS
    Hozzáférés
    1.28
    Datuak
    1.23
     resourceCulture
    1.13
    rungsseite
    1.10
    دانشنامهٔ
    1.10
     дописавши
    1.07
     ExecuteAsync
    1.07
    ReusableCell
    1.06
     nakalista
    1.06
    +#+#
    1.04
    Act Density 0.229%

    No Known Activations