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

    Neuronpedia

    INDEX
    Explanations

    academic citations and research papers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Zumba
    0.90
     SharePoint
    0.84
     Karen
    0.84
     Bollywood
    0.84
     ADHD
    0.82
     Guam
    0.82
     caters
    0.82
     Magento
    0.81
     was
    0.81
     Côte
    0.80
    POSITIVE LOGITS
    arxiv
    1.13
    PhysRev
    1.05
    arXiv
    0.88
    TimeSeries
    0.86
    tikz
    0.80
    gaussian
    0.79
    physics
    0.78
    freq
    0.77
    libro
    0.77
    pdf
    0.76
    Act Density 0.078%

    No Known Activations