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

    Neuronpedia

    INDEX
    Explanations

    Code, memory allocation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    attached
    -0.09
    在人
    -0.08
     attached
    -0.08
     ora
    -0.08
     Buena
    -0.08
     nostra
    -0.07
     किं
    -0.07
     voie
    -0.07
    τού
    -0.07
     perde
    -0.07
    POSITIVE LOGITS
     spread
    0.09
    <Get
    0.09
    	memset
    0.09
    (Search
    0.09
    Spread
    0.08
     spreads
    0.08
    <Search
    0.08
    xffff
    0.08
    .Sequential
    0.08
    spread
    0.08
    Act Density 0.002%

    No Known Activations