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

    Neuronpedia

    INDEX
    Explanations

    economics

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Starr
    -0.07
    ovaného
    -0.06
     Lithuania
    -0.06
     Mustafa
    -0.06
    Capture
    -0.06
     decorated
    -0.06
    /car
    -0.06
     Patrick
    -0.06
    Nice
    -0.06
    .Measure
    -0.06
    POSITIVE LOGITS
     شر
    0.06
     appellant
    0.06
     disrespectful
    0.06
     membr
    0.06
    HasForeignKey
    0.06
    �
    0.06
     immigr
    0.06
     精
    0.06
    netinet
    0.06
     Destructor
    0.06
    Act Density 0.124%

    No Known Activations