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

    Neuronpedia

    INDEX
    Explanations

    rel="

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Балтбет
    0.61
     Шта
    0.56
    periods
    0.56
    fad
    0.53
    伟大
    0.51
    oppositions
    0.51
     Ради
    0.50
    incredible
    0.50
    headings
    0.50
    വ്ര
    0.50
    POSITIVE LOGITS
     peste
    0.65
     fixer
    0.64
     pact
    0.61
     qa
    0.60
     consumer
    0.60
     cual
    0.58
     carat
    0.57
     geï
    0.57
     fairy
    0.56
     molecule
    0.56
    Act Density 0.000%

    No Known Activations