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
    730
    -0.07
     describing
    -0.07
     requisite
    -0.07
    ThanOr
    -0.07
    ーナ
    -0.06
    	parse
    -0.06
     Plates
    -0.06
     馬
    -0.06
     dead
    -0.06
    这是
    -0.06
    POSITIVE LOGITS
     عالية
    0.07
    шки
    0.07
     бла
    0.07
    ividual
    0.07
    zerbai
    0.07
    ､_
    0.06
     Tổ
    0.06
    ottie
    0.06
    퓨
    0.06
    GMEM
    0.06
    Act Density 0.192%

    No Known Activations