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

    Neuronpedia

    INDEX
    Explanations

    is

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    فس
    -0.07
     salud
    -0.07
    	sn
    -0.06
    英雄
    -0.06
    VRT
    -0.06
    ulers
    -0.06
    (selector
    -0.06
     Сам
    -0.06
    ้ส
    -0.06
    олом
    -0.06
    POSITIVE LOGITS
     Selection
    0.06
     Zhou
    0.06
     grappling
    0.06
    tracer
    0.06
     Moses
    0.06
      ↵
    0.06
     intercourse
    0.06
     اتاق
    0.06
     免
    0.06
     Tomáš
    0.06
    Act Density 0.049%

    No Known Activations