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

    Neuronpedia

    INDEX
    Explanations

    Questions and answers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Silent
    -0.07
     Analytics
    -0.06
    رد
    -0.06
     analytics
    -0.06
    уда
    -0.06
     aDecoder
    -0.06
    _confirmation
    -0.06
    )?$
    -0.06
    ==-
    -0.06
    NECT
    -0.06
    POSITIVE LOGITS
    types
    0.07
    ажд
    0.07
    strained
    0.07
     下跌
    0.06
    还有
    0.06
    テ
    0.06
     sources
    0.06
    一年
    0.06
    ８
    0.06
    енная
    0.06
    Act Density 0.000%

    No Known Activations