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

    Neuronpedia

    INDEX
    Explanations

    concepts and discussions related to democracy

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

    democracy and its ideals

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    +#+#
    -1.36
    [@BOS@]
    -1.02
    <unused16>
    -1.02
    <unused41>
    -1.02
    <unused42>
    -1.02
    <pad>
    -1.02
    <unused8>
    -1.02
    <unused28>
    -1.02
    <unused43>
    -1.02
    <unused23>
    -1.02
    POSITIVE LOGITS
     democracy
    0.34
     fundamental
    0.28
     
    0.27
     basic
    0.27
     human
    0.27
     instituições
    0.26
     .
    0.26
    ,
    0.26
    <i>
    0.26
    casila
    0.25
    Act Density 0.052%

    No Known Activations