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

    Neuronpedia

    INDEX
    Explanations

    Questions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	player
    -0.07
     Bedrooms
    -0.07
     scared
    -0.07
     stocked
    -0.07
     pracov
    -0.06
     参考
    -0.06
    	Write
    -0.06
     GameObject
    -0.06
     поход
    -0.06
     startPosition
    -0.06
    POSITIVE LOGITS
    Traditional
    0.07
    etros
    0.06
     churn
    0.06
    ertest
    0.06
    태
    0.06
    การศ
    0.06
    istream
    0.06
     ori
    0.06
     carbohydrates
    0.06
    _multi
    0.06
    Act Density 0.063%

    No Known Activations