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

    Neuronpedia

    INDEX
    Explanations

    scientific publications

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     strained
    -0.07
     maar
    -0.06
     фото
    -0.06
     skins
    -0.06
    -',
    -0.06
    .GetFiles
    -0.06
     convict
    -0.05
     OU
    -0.05
    ’l
    -0.05
     adam
    -0.05
    POSITIVE LOGITS
     глав
    0.07
    .Pixel
    0.06
     CPI
    0.06
    知道
    0.06
    -known
    0.06
    eming
    0.06
     retire
    0.06
    awai
    0.06
    ALLE
    0.06
     gloss
    0.06
    Act Density 0.004%

    No Known Activations