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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    氧气
    -0.08
    NEWS
    -0.07
     excell
    -0.07
    艰辛
    -0.07
     didnt
    -0.07
    Test
    -0.07
    每次
    -0.07
     blood
    -0.07
    重复
    -0.07
     fresh
    -0.07
    POSITIVE LOGITS
     paramName
    0.07
    垚
    0.07
    ﾅ
    0.07
    峱
    0.07
     builder
    0.07
     historians
    0.07
     khắc
    0.07
    峡谷
    0.06
    ко
    0.06
     הצטר
    0.06
    Act Density 0.003%

    No Known Activations