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

    Neuronpedia

    INDEX
    Explanations

    a

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .GetInstance
    -0.07
    行動
    -0.07
     začí
    -0.06
    ASC
    -0.06
     更新
    -0.06
    責
    -0.06
     فبراير
    -0.06
    ald
    -0.06
    ินเด
    -0.06
    diet
    -0.06
    POSITIVE LOGITS
     magic
    0.07
    .azure
    0.07
     Shoulder
    0.06
     Actions
    0.06
     intervals
    0.06
     usual
    0.06
    266
    0.06
     scheme
    0.06
     noun
    0.06
     constituent
    0.06
    Act Density 0.019%

    No Known Activations