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

    Neuronpedia

    INDEX
    Explanations

    ensa

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     blink
    -0.06
    力
    -0.06
    ("../
    -0.06
    (host
    -0.06
     whichever
    -0.06
    Transmission
    -0.06
     $↵↵
    -0.06
    	Size
    -0.06
     všech
    -0.06
    шим
    -0.06
    POSITIVE LOGITS
     граду
    0.07
    书记
    0.07
    .Reporting
    0.07
     Pierre
    0.06
     Escorts
    0.06
     TableView
    0.06
     dönemde
    0.06
     들어
    0.06
    (coeff
    0.06
     působ
    0.06
    Act Density 0.019%

    No Known Activations