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

    Neuronpedia

    INDEX
    Explanations

    .

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    本事
    -0.07
     ambigu
    -0.07
    一方面
    -0.07
    こと
    -0.07
    itemName
    -0.07
     אני
    -0.06
    ც
    -0.06
    얘
    -0.06
     nieuwe
    -0.06
    謂
    -0.06
    POSITIVE LOGITS
     unzip
    0.07
     Laurel
    0.07
     drink
    0.07
     weed
    0.06
     sugar
    0.06
     Buy
    0.06
     responsibly
    0.06
    冷藏
    0.06
     IHttp
    0.06
     foul
    0.06
    Act Density 0.017%

    No Known Activations