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

    Neuronpedia

    INDEX
    Explanations

    web

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    /mock
    -0.06
    	tile
    -0.06
    Lake
    -0.06
     Gauss
    -0.06
    	display
    -0.06
     Sek
    -0.06
     Lake
    -0.06
    (change
    -0.06
    _ak
    -0.06
     catast
    -0.06
    POSITIVE LOGITS
     abdom
    0.08
     web
    0.07
    蜘蛛
    0.07
    ethical
    0.07
    킬
    0.07
    ObjectContext
    0.06
    .ant
    0.06
     webs
    0.06
     vz
    0.06
    .web
    0.06
    Act Density 0.001%

    No Known Activations