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

    Neuronpedia

    INDEX
    Explanations

    with

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    bin
    -0.07
     Suffolk
    -0.06
     Almighty
    -0.06
    ρούν
    -0.06
    outfile
    -0.06
    _Function
    -0.06
    .program
    -0.06
    	cf
    -0.06
     обол
    -0.06
    icies
    -0.06
    POSITIVE LOGITS
    =A
    0.06
     레이
    0.06
    _TH
    0.06
    UMP
    0.06
    [K
    0.06
     NO
    0.06
    Room
    0.06
     Although
    0.06
     주문
    0.06
     benefici
    0.06
    Act Density 0.001%

    No Known Activations