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

    Neuronpedia

    INDEX
    Explanations

    articles

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     filament
    -0.08
     kde
    -0.07
    	count
    -0.07
     але
    -0.07
     Maze
    -0.07
    雅
    -0.06
    -backend
    -0.06
    omy
    -0.06
    امي
    -0.06
     tones
    -0.06
    POSITIVE LOGITS
     HttpHeaders
    0.07
     человеч
    0.06
     عص
    0.06
     đai
    0.06
     reorder
    0.06
     chống
    0.06
     декабря
    0.06
     Chí
    0.06
     Türkçe
    0.06
    μάτων
    0.06
    Act Density 0.132%

    No Known Activations