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

    Neuronpedia

    INDEX
    Explanations

    have

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ניוז
    -0.07
    疫情影响
    -0.06
     הקו
    -0.06
     Extremely
    -0.06
    ⥹
    -0.06
     estava
    -0.06
    胖
    -0.06
    earch
    -0.06
     منطقة
    -0.06
    Vision
    -0.06
    POSITIVE LOGITS
    ulo
    0.08
     Heap
    0.08
    singleton
    0.08
     Analyzer
    0.07
    给了
    0.07
    cale
    0.07
    =admin
    0.07
     mqtt
    0.07
     conte
    0.07
     prob
    0.07
    Act Density 0.027%

    No Known Activations