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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     сторон
    -0.06
     μπορεί
    -0.06
     '#
    -0.06
     seriously
    -0.06
     frank
    -0.06
    	className
    -0.06
    {x
    -0.06
    ifornia
    -0.06
     il
    -0.06
    userid
    -0.06
    POSITIVE LOGITS
     Symbols
    0.07
     ReturnValue
    0.06
     Hoy
    0.06
     Sapphire
    0.06
     limits
    0.06
     EF
    0.06
     هدف
    0.06
    σσα
    0.06
    QueryParam
    0.06
    ELLOW
    0.06
    Act Density 0.258%

    No Known Activations