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

    Neuronpedia

    INDEX
    Explanations

    clarify

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     прек
    -0.08
     pun
    -0.07
     getById
    -0.07
    srv
    -0.06
    tables
    -0.06
     vested
    -0.06
     Changed
    -0.06
     propri
    -0.06
    яз
    -0.06
     freezes
    -0.06
    POSITIVE LOGITS
     Absolutely
    0.06
    crawl
    0.06
     compromised
    0.06
    .Axis
    0.06
     allow
    0.06
    .graph
    0.06
    आई
    0.06
     gön
    0.06
    .Home
    0.06
    igth
    0.06
    Act Density 0.016%

    No Known Activations