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

    Neuronpedia

    INDEX
    Explanations

    Problems and solutions

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     tiene
    -0.07
    preserve
    -0.07
    iedades
    -0.07
     vn
    -0.07
    知识
    -0.07
     лучше
    -0.07
    icular
    -0.07
    anter
    -0.06
    ieran
    -0.06
    涵
    -0.06
    POSITIVE LOGITS
    RequestMethod
    0.07
     Birth
    0.07
    compan
    0.06
    前行
    0.06
    黄河
    0.06
    شق
    0.06
    )init
    0.06
     saúde
    0.06
    .autoconfigure
    0.06
     riding
    0.06
    Act Density 0.279%

    No Known Activations