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

    Neuronpedia

    INDEX
    Explanations

    summary

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (":
    -0.07
     sonra
    -0.07
    $("#
    -0.07
    香港
    -0.06
    uyễn
    -0.06
    лід
    -0.06
     artifacts
    -0.06
     emperor
    -0.06
     Emperor
    -0.06
    たく
    -0.06
    POSITIVE LOGITS
    icontains
    0.08
     />\
    0.07
    andalone
    0.06
    電視
    0.06
     Totally
    0.06
     wipes
    0.06
    ortex
    0.06
    .Axis
    0.06
    //{↵
    0.05
    ющий
    0.05
    Act Density 0.001%

    No Known Activations