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

    Neuronpedia

    INDEX
    Explanations

    political

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Interesting
    -0.07
     Cardiff
    -0.06
    丈夫
    -0.06
    说道
    -0.06
    Neal
    -0.06
    because
    -0.06
     Roof
    -0.06
    ете
    -0.06
     že
    -0.06
    umi
    -0.06
    POSITIVE LOGITS
    شناس
    0.06
     prere
    0.06
     synd
    0.06
     gating
    0.06
     Distributed
    0.06
     comet
    0.06
     ud
    0.06
    ेब
    0.06
     //================================================================
    0.06
     COS
    0.06
    Act Density 0.072%

    No Known Activations