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

    Neuronpedia

    INDEX
    Explanations

    references to publications and their details

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

    Preceding punctuation, especially quotation marks and parentheses

    np_acts-logits-general · gemini-2.0-flash

    questions starting with Q

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ngdoc
    -0.66
     Autorizaciones
    -0.62
     ffilmiau
    -0.61
    しくは
    -0.56
    Twas
    -0.54
    ték
    -0.54
     bağı
    -0.52
     عظ
    -0.52
    Phys
    -0.51
     commerciaux
    -0.50
    POSITIVE LOGITS
     argues
    0.67
     passim
    0.64
     argued
    0.63
    elemField
    0.60
     essays
    0.59
    complexContent
    0.56
     argue
    0.55
     arguing
    0.54
    Personendaten
    0.53
    Forth
    0.53
    Act Density 0.198%

    No Known Activations