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

    Neuronpedia

    INDEX
    Explanations

    period

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    申请
    -0.07
    Head
    -0.07
    NSE
    -0.06
     MSI
    -0.06
    	sem
    -0.06
    ۱۱
    -0.06
     Licence
    -0.06
    ibrate
    -0.06
     určit
    -0.06
    desc
    -0.06
    POSITIVE LOGITS
    人的
    0.06
    めた
    0.06
     hơi
    0.06
     doctrines
    0.06
    ुह
    0.06
     >
    0.06
    ��드
    0.06
     rows
    0.06
     оскільки
    0.06
     المخت
    0.06
    Act Density 0.008%

    No Known Activations