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

    Neuronpedia

    INDEX
    Explanations

    Argentine club, American president

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    emphas
    1.08
     astrocytes
    1.04
    ‚‚
    1.02
    weil
    1.01
    लाई
    1.00
     zaradi
    1.00
     erau
    1.00
     sexu
    0.98
    我们将
    0.97
     surve
    0.96
    POSITIVE LOGITS
    者的
    1.29
     noticed
    1.27
    者に
    1.25
    者の
    1.15
     BadRequest
    1.11
    blade
    1.11
     boulder
    1.10
    者
    1.10
     বিনামূল্যে
    1.09
     않은
    1.08
    Act Density 0.000%

    No Known Activations