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

    Neuronpedia

    INDEX
    Explanations

    Unstructured text

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    σον
    -0.07
    ､_
    -0.07
     نار
    -0.07
     spotting
    -0.06
     luxurious
    -0.06
     미
    -0.06
    Blo
    -0.06
     falta
    -0.06
     alive
    -0.06
     nationality
    -0.06
    POSITIVE LOGITS
     Differences
    0.06
     yetiş
    0.06
     MacOS
    0.06
     configurable
    0.06
     foundational
    0.06
    mmc
    0.06
    äter
    0.06
     adequ
    0.06
    	path
    0.06
    angles
    0.06
    Act Density 0.012%

    No Known Activations