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

    Neuronpedia

    INDEX
    Explanations

    common people

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     nast
    -0.07
     palabras
    -0.07
    tracking
    -0.07
     BUY
    -0.07
    居
    -0.06
    erot
    -0.06
     urlencode
    -0.06
     Hydraulic
    -0.06
    	p
    -0.06
     полов
    -0.06
    POSITIVE LOGITS
    .signup
    0.06
     obr
    0.06
    Assembler
    0.06
    =dict
    0.06
     akin
    0.06
    quartered
    0.06
     dáng
    0.06
    /NĐ
    0.06
    zeň
    0.06
    _detected
    0.06
    Act Density 0.062%

    No Known Activations