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

    Neuronpedia

    INDEX
    Explanations

    acronym explanations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     has
    1.26
     and
    1.15
     had
    1.07
     is
    1.05
     have
    1.05
     haunts
    1.02
     seems
    1.02
     lesions
    1.01
     been
    1.00
     fixtures
    0.98
    POSITIVE LOGITS
    创新
    1.18
    imagine
    1.14
    Program
    1.09
    organizzazione
    1.09
    sprogram
    1.08
    取り組み
    1.07
    evoluzione
    1.05
    program
    1.04
     Plattform
    1.03
     иннова
    1.03
    Act Density 0.527%

    No Known Activations