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

    Neuronpedia

    INDEX
    Explanations

    foreign words and names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     arXiv
    0.52
     PLoS
    0.46
     Bayesian
    0.44
    提案
    0.44
     phytochemical
    0.44
    )$
    0.42
     murine
    0.42
     Unpublished
    0.42
     PubMed
    0.42
    arXiv
    0.41
    POSITIVE LOGITS
     falle
    0.41
    赸
    0.40
    тов
    0.39
    फ़
    0.39
    挍
    0.39
     gjennom
    0.38
     babe
    0.38
    рь
    0.38
    -'].
    0.38
    اع
    0.37
    Act Density 0.035%

    No Known Activations