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

    Neuronpedia

    INDEX
    Explanations

    key phrases and terminology associated with democracy and governance

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

    preceding titles or capitalized words

    np_acts-logits-general · gemini-2.0-flash

    books titles and descriptions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     }}$}
    -0.55
     виправивши
    -0.54
    สบ
    -0.51
    onaceous
    -0.50
     apapun
    -0.50
    %">
    -0.49
     själ
    -0.49
     själva
    -0.47
    Operate
    -0.47
     Ersten
    -0.45
    POSITIVE LOGITS
     which
    0.80
     >=",
    0.80
    which
    0.69
     ซึ่ง
    0.68
     című
    0.67
    ?,
    0.67
    AndEndTag
    0.66
     wherein
    0.65
    !,
    0.65
     Similarly
    0.63
    Act Density 1.470%

    No Known Activations