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

    Neuronpedia

    INDEX
    Explanations

    private

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     наиболее
    -0.06
    иболее
    -0.06
     ł
    -0.06
    -col
    -0.06
     nk
    -0.06
    _center
    -0.06
     emo
    -0.06
    ीब
    -0.06
    college
    -0.06
    outputs
    -0.06
    POSITIVE LOGITS
    	main
    0.07
    worked
    0.06
    (items
    0.06
     equals
    0.06
    �
    0.06
    apons
    0.06
     UPPER
    0.06
     oli
    0.06
    icích
    0.06
     prepares
    0.06
    Act Density 0.004%

    No Known Activations