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

    Neuronpedia

    INDEX
    Explanations

    references to legal citations and bibliographic entries

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

    citations omitted

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    M
    -0.41
    E
    -0.41
     negeri
    -0.39
     armée
    -0.38
    -
    -0.36
    <b>
    -0.36
    Over
    -0.36
    MS
    -0.36
    m
    -0.36
    i
    -0.35
    POSITIVE LOGITS
     citation
    2.41
     Citation
    2.36
     citations
    2.17
     Citations
    2.06
    citation
    1.99
    Citation
    1.87
    citations
    1.67
    Citations
    1.59
    CITATION
    1.46
     Cit
    1.03
    Act Density 0.013%

    No Known Activations