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

    Neuronpedia

    INDEX
    Explanations

    instrument

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    偏
    -0.08
     वस
    -0.07
    (issue
    -0.07
    charg
    -0.06
    endar
    -0.06
     station
    -0.06
    aşı
    -0.06
    박
    -0.06
     Patt
    -0.06
     trains
    -0.06
    POSITIVE LOGITS
     interviewer
    0.07
     Courier
    0.06
     参数
    0.06
     nguồn
    0.06
    {}'.
    0.06
     coordin
    0.06
    appa
    0.06
    lıyor
    0.06
     관련
    0.06
     لع
    0.06
    Act Density 0.031%

    No Known Activations