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

    Neuronpedia

    INDEX
    Explanations

    early computing and internet

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Arbor
    -0.07
    那么
    -0.07
     biodiversity
    -0.07
    -columns
    -0.06
     Pane
    -0.06
     aggregate
    -0.06
    stal
    -0.06
    Stretch
    -0.06
    iples
    -0.06
    imon
    -0.06
    POSITIVE LOGITS
     留
    0.07
     Brendan
    0.07
    =output
    0.06
     bbc
    0.06
    ngo
    0.06
     flags
    0.06
     FE
    0.06
     flag
    0.06
    =res
    0.06
    =event
    0.06
    Act Density 0.187%

    No Known Activations