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

    Neuronpedia

    INDEX
    Explanations

    comma

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (Calendar
    -0.06
    цион
    -0.06
     transfer
    -0.06
    .getZ
    -0.06
    连
    -0.06
     Mandarin
    -0.06
     offense
    -0.06
    ظٹط
    -0.06
     Jacobs
    -0.06
    	writer
    -0.06
    POSITIVE LOGITS
     setType
    0.06
     Histor
    0.06
     of
    0.06
    体育
    0.06
     mour
    0.06
    (ofSize
    0.06
     ayn
    0.06
    lernen
    0.06
    .hour
    0.06
     preced
    0.06
    Act Density 0.013%

    No Known Activations