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

    Neuronpedia

    INDEX
    Explanations

    code/data formatting

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     sluggish
    -0.08
     domic
    -0.08
     squared
    -0.08
     squares
    -0.08
     difficult
    -0.07
    /repos
    -0.07
     territor
    -0.07
     bolsillo
    -0.07
     संस
    -0.07
     bounded
    -0.07
    POSITIVE LOGITS
    (header
    0.14
     header
    0.13
     headers
    0.13
    	headers
    0.13
    	header
    0.13
    /header
    0.12
    .header
    0.12
    =headers
    0.12
    thead
    0.12
     encabez
    0.11
    Act Density 0.007%

    No Known Activations