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

    Neuronpedia

    INDEX
    Explanations

    /

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _BEGIN
    -0.09
     perpet
    -0.09
    _apps
    -0.07
    سوء
    -0.07
     Earl
    -0.07
    ительн
    -0.07
     ye
    -0.07
    还不
    -0.07
     essere
    -0.07
     perpetual
    -0.07
    POSITIVE LOGITS
     oven
    0.07
     activated
    0.07
    rias
    0.07
     Modifications
    0.07
    DONE
    0.07
    加班
    0.07
    stop
    0.06
    	Scanner
    0.06
    	Input
    0.06
    Investigators
    0.06
    Act Density 0.001%

    No Known Activations