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

    Neuronpedia

    INDEX
    Explanations

    political interference

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Chel
    -0.08
     Songs
    -0.08
    /mol
    -0.08
    mongoose
    -0.08
    ulator
    -0.08
    Songs
    -0.08
    constructor
    -0.08
     VGA
    -0.07
     prelim
    -0.07
     payable
    -0.07
    POSITIVE LOGITS
     misinformation
    0.12
     ट्विटर
    0.12
     ट्वीट
    0.11
     tweet
    0.10
     फेसबुक
    0.10
     extremist
    0.10
     tweets
    0.10
     tweeting
    0.09
     partisan
    0.09
     Ultra
    0.09
    Act Density 0.020%

    No Known Activations