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

    Neuronpedia

    INDEX
    Explanations

    under

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     MSR
    -0.07
    ifo
    -0.07
    加载
    -0.07
     crowd
    -0.07
     внимание
    -0.06
    .Async
    -0.06
     JPG
    -0.06
    粝
    -0.06
    iji
    -0.06
     blessing
    -0.06
    POSITIVE LOGITS
    是一位
    0.08
     chapters
    0.08
    sales
    0.07
     Seymour
    0.07
     Thur
    0.07
    风水
    0.07
     Dudley
    0.07
    发扬
    0.07
    ENCIES
    0.06
    -depth
    0.06
    Act Density 0.004%

    No Known Activations