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

    Neuronpedia

    INDEX
    Explanations

    Code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Cumhuriyet
    -0.07
     spyOn
    -0.07
     Erd
    -0.06
     Forrest
    -0.06
    styl
    -0.06
     хто
    -0.06
    광고
    -0.06
    .LatLng
    -0.06
     CCP
    -0.06
     construed
    -0.06
    POSITIVE LOGITS
     Historic
    0.08
     re
    0.07
    	rc
    0.07
    Ret
    0.06
    وروب
    0.06
    ffi
    0.06
    annual
    0.06
    vrolet
    0.06
    静
    0.06
    수로
    0.06
    Act Density 0.024%

    No Known Activations