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

    Neuronpedia

    INDEX
    Explanations

    client

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    iene
    -0.07
     offered
    -0.06
     written
    -0.06
     ngành
    -0.06
     affidavit
    -0.06
     نوشته
    -0.06
     streets
    -0.06
     vegetables
    -0.06
    Since
    -0.06
    次数
    -0.06
    POSITIVE LOGITS
    386
    0.08
     embodiments
    0.07
    左
    0.07
    AdapterManager
    0.06
     zaháj
    0.06
     și
    0.06
     Composer
    0.06
     enthus
    0.06
    ,I
    0.06
    %",
    0.06
    Act Density 0.005%

    No Known Activations