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

    Neuronpedia

    INDEX
    Explanations

    embed

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     lines
    -0.06
    ẵ
    -0.06
     getPage
    -0.06
     singer
    -0.06
    	elif
    -0.06
     หร
    -0.05
     spoken
    -0.05
    718
    -0.05
     speak
    -0.05
    -control
    -0.05
    POSITIVE LOGITS
     impressive
    0.07
     vir
    0.07
     тепер
    0.07
    miyor
    0.07
    ड़क
    0.07
     mie
    0.07
    ")){
↵
    0.06
    ечение
    0.06
     ویژه
    0.06
    (ERROR
    0.06
    Act Density 0.003%

    No Known Activations