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

    Neuronpedia

    INDEX
    Explanations

    scientific publications

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     POR
    -0.07
    258
    -0.06
     داشت
    -0.06
    avo
    -0.06
    558
    -0.06
     seq
    -0.06
    您的
    -0.06
    ursal
    -0.06
     exemple
    -0.06
     intensive
    -0.06
    POSITIVE LOGITS
    ，並
    0.07
    沖
    0.06
    ิ์
    0.06
     nedenle
    0.06
    言
    0.06
     ApiService
    0.06
    启
    0.06
    جی
    0.06
     firefighter
    0.06
     açı
    0.06
    Act Density 0.028%

    No Known Activations