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

    Neuronpedia

    INDEX
    Explanations

    III

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ghetto
    -0.07
    Ģ
    -0.06
    oger
    -0.06
    retim
    -0.06
     dağ
    -0.06
    Performed
    -0.06
     eventName
    -0.06
     Spare
    -0.06
     programa
    -0.06
     posto
    -0.06
    POSITIVE LOGITS
     Equity
    0.07
    ettings
    0.06
     Benchmark
    0.06
     objective
    0.06
            ↵        ↵
    0.06
     Ticket
    0.06
    	rc
    0.06
     qualified
    0.06
    zew
    0.06
     servicing
    0.06
    Act Density 0.003%

    No Known Activations