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

    Neuronpedia

    INDEX
    Explanations

    frequent articles and common prepositions in text

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

    possessive `'s` or `the` followed by noun

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    //
    -0.42
    package
    -0.41
     kohdetta
    -0.40
     Zustimmung
    -0.37
     servire
    -0.36
    astanza
    -0.36
    ⓧ
    -0.35
    <?
    -0.34
    __
    -0.34
     Cummings
    -0.34
    POSITIVE LOGITS
    SequentialGroup
    0.63
    Халык
    0.62
     nakalista
    0.60
    Datuak
    0.59
    KommentareTeilen
    0.59
     estekak
    0.59
     חיצוניים
    0.59
    তথ্যসূত্র
    0.59
    httphttps
    0.57
    rungsseite
    0.54
    Act Density 0.610%

    No Known Activations