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

    Neuronpedia

    INDEX
    Explanations

    references to governance and the role of the public in society

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

    user turns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     queſta
    -1.21
     パンチラ
    -1.19
    <unused23>
    -1.19
    <unused47>
    -1.19
    <unused16>
    -1.18
    <unused14>
    -1.18
    <unused28>
    -1.18
    <unused42>
    -1.18
    [@BOS@]
    -1.18
    <unused8>
    -1.18
    POSITIVE LOGITS
     [
    0.35
    ,
    0.34
     
    0.30
     &
    0.29
    <eos>
    0.28
     to
    0.26
     .
    0.26
     de
    0.25
     l
    0.24
     (
    0.24
    Act Density 0.123%

    No Known Activations