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

    Neuronpedia

    INDEX
    Explanations

    version

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Prem
    -0.07
    	Function
    -0.07
    crear
    -0.06
     positives
    -0.06
    Sizer
    -0.06
     propre
    -0.06
     partir
    -0.06
    	has
    -0.06
    DM
    -0.06
    	C
    -0.06
    POSITIVE LOGITS
    ptune
    0.07
     "]");↵
    0.06
    hw
    0.06
    عات
    0.06
    IQ
    0.06
    skb
    0.06
    ounce
    0.06
    님이
    0.06
    exampleModal
    0.06
    ху
    0.06
    Act Density 0.000%

    No Known Activations