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

    Neuronpedia

    INDEX
    Explanations

    awards

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     useClass
    -0.07
    soc
    -0.06
    er
    -0.06
    çiler
    -0.06
    ८
    -0.06
     //#
    -0.06
     barcode
    -0.06
    译
    -0.06
     möglich
    -0.06
    variables
    -0.06
    POSITIVE LOGITS
     sport
    0.07
     ville
    0.06
     potent
    0.06
     fontSize
    0.06
    旅行
    0.06
    atta
    0.06
    lut
    0.06
     appoint
    0.06
     بيت
    0.06
    ้วย
    0.06
    Act Density 0.015%

    No Known Activations