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

    Neuronpedia

    INDEX
    Explanations

    question answer forum

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ГО
    -0.07
     flattering
    -0.06
    utos
    -0.06
    公司
    -0.06
    _many
    -0.06
     wat
    -0.06
    uely
    -0.06
    nier
    -0.06
    mek
    -0.06
     toArray
    -0.06
    POSITIVE LOGITS
     presumably
    0.06
     чи
    0.06
    сии
    0.06
    \Factories
    0.06
    .activate
    0.06
    Ball
    0.06
    redit
    0.05
    서관
    0.05
     Goes
    0.05
     testData
    0.05
    Act Density 0.289%

    No Known Activations