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

    Neuronpedia

    INDEX
    Explanations

    occurrences of prepositions and conjunctions in the text

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

    Prepositions "in", "with", "at", and "from"

    np_acts-logits-general · gemini-2.0-flash

    chemical element indexing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ésultats
    -1.12
    <unused14>
    -1.12
    <pad>
    -1.11
    [@BOS@]
    -1.11
    <unused42>
    -1.11
    <unused74>
    -1.11
    <unused41>
    -1.11
    <unused28>
    -1.11
    <unused8>
    -1.11
    <unused23>
    -1.11
    POSITIVE LOGITS
    ,
    0.54
    -
    0.45
    +
    0.44
    </h3>
    0.41
     and
    0.38
    入
    0.38
    ，
    0.37
    In
    0.37
     On
    0.37
     &
    0.37
    Act Density 0.549%

    No Known Activations