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

    Neuronpedia

    INDEX
    Explanations

    more

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    颤
    -0.08
     jes
    -0.07
     Utils
    -0.07
    钆
    -0.07
     intimidate
    -0.07
    (rect
    -0.07
    揶
    -0.07
    itim
    -0.07
    ]};↵
    -0.07
     erw
    -0.07
    POSITIVE LOGITS
     товар
    0.06
     מס
    0.06
    documents
    0.06
    منظومة
    0.06
    וז
    0.06
    相比于
    0.06
    发生了
    0.06
     interés
    0.06
     booking
    0.06
    וכ
    0.06
    Act Density 0.054%

    No Known Activations