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

    Neuronpedia

    INDEX
    Explanations

    into

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    UNDLE
    -0.07
    雞
    -0.07
     categoria
    -0.07
    SELL
    -0.07
     Toni
    -0.07
    ⬛
    -0.07
    所提供的
    -0.07
    称为
    -0.07
    久しぶり
    -0.07
    生态系统
    -0.06
    POSITIVE LOGITS
     Princeton
    0.07
    檀
    0.07
    лон
    0.07
     dateFormat
    0.07
     Jonah
    0.07
     One
    0.07
    淀
    0.07
     Analytics
    0.07
     FILTER
    0.06
    remark
    0.06
    Act Density 0.024%

    No Known Activations