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

    Neuronpedia

    INDEX
    Explanations

    HTML code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ard
    -0.07
    (h
    -0.07
     Bam
    -0.07
     lining
    -0.06
    Bush
    -0.06
     Holdings
    -0.06
     Thousand
    -0.06
     pounds
    -0.06
     feedback
    -0.06
     efficiently
    -0.06
    POSITIVE LOGITS
     rizik
    0.07
     tutti
    0.07
    ню
    0.06
    buquerque
    0.06
     管
    0.06
    cciones
    0.06
     gọn
    0.06
     особи
    0.06
     хозя
    0.06
     già
    0.06
    Act Density 0.143%

    No Known Activations