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

    Neuronpedia

    INDEX
    Explanations

    headed

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     некоторое
    -0.09
     మధ్య
    -0.08
     évolution
    -0.08
     temiz
    -0.07
     geeignet
    -0.07
     complements
    -0.07
     excursion
    -0.07
     umi
    -0.07
     Zeit
    -0.07
     간
    -0.07
    POSITIVE LOGITS
    、多
    0.13
    ultiple
    0.11
     متعددة
    0.10
    _multiple
    0.10
    -three
    0.10
     múltiples
    0.10
    .Multi
    0.10
    ulti
    0.10
     متعدد
    0.10
    multiple
    0.10
    Act Density 0.038%

    No Known Activations