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

    Neuronpedia

    INDEX
    Explanations

    titles and references related to academic or literary works

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

    Content within parentheses, especially citations

    np_acts-logits-general · gemini-2.0-flash

    citations like "id."

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ngdoc
    -0.64
    Twas
    -0.59
     ffilmiau
    -0.59
     Autorizaciones
    -0.58
    zwald
    -0.58
    StreetMap
    -0.55
    InitVars
    -0.53
    ientí
    -0.50
    ![](
    -0.48
     (*.
    -0.48
    POSITIVE LOGITS
     passim
    0.80
     argues
    0.77
     idem
    0.67
     forthcoming
    0.67
     argued
    0.67
    eafter
    0.67
     reprinted
    0.65
     essays
    0.63
     qtd
    0.62
     ibid
    0.60
    Act Density 0.303%

    No Known Activations