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

    Neuronpedia

    INDEX
    Explanations

    followed and

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    💹
    -0.08
    foregroundColor
    -0.08
    匮
    -0.07
     Burg
    -0.07
     backgroundColor
    -0.07
     sponsored
    -0.07
    멥
    -0.07
    	driver
    -0.07
    負け
    -0.07
    主题
    -0.07
    POSITIVE LOGITS
    Pipe
    0.08
     weekends
    0.07
    IRO
    0.07
    dead
    0.07
    ряд
    0.07
     tens
    0.07
    -Russian
    0.07
    water
    0.07
     dönemin
    0.06
    טיפול
    0.06
    Act Density 0.013%

    No Known Activations