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

    Neuronpedia

    INDEX
    Explanations

    a combination of positive adjectives, review-like phrases, and the word 'the'.

    oai_token-act-pair · gemini-2.0-flash

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     obstante
    -0.54
     coppia
    -0.51
    queryInterface
    -0.48
     monnaie
    -0.47
     démocr
    -0.46
     bezoek
    -0.46
    AllowAnonymous
    -0.46
     circonst
    -0.46
     exécu
    -0.45
     fièvre
    -0.45
    POSITIVE LOGITS
    <bos>
    0.66
    ")){
    0.65
    Portale
    0.62
     rest
    0.62
    cillors
    0.61
    :^{
    0.60
    "){
    0.58
    ("$.
    0.58
     ra
    0.57
    '){
    0.57
    Act Density 1.335%

    No Known Activations