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

    Neuronpedia

    INDEX
    Explanations

    historical facts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ley
    -0.07
    дон
    -0.07
    untos
    -0.07
    ete
    -0.07
    LEY
    -0.06
     буде
    -0.06
     сов
    -0.06
     uyg
    -0.06
    این
    -0.06
    _nv
    -0.06
    POSITIVE LOGITS
    expression
    0.06
     ohio
    0.06
    hdl
    0.06
     pollut
    0.06
    	Service
    0.06
    _processed
    0.06
    　l
    0.06
    ClickListener
    0.06
    menuItem
    0.06
    industry
    0.06
    Act Density 0.048%

    No Known Activations