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

    Neuronpedia

    INDEX
    Explanations

    public

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     dracon
    -0.07
    ダイ
    -0.07
    irling
    -0.06
     территории
    -0.06
     přízn
    -0.06
    ерим
    -0.06
     rivers
    -0.06
     vertically
    -0.06
     differently
    -0.06
    isdiction
    -0.06
    POSITIVE LOGITS
     Tobacco
    0.08
     protected
    0.07
    WhatsApp
    0.07
    	protected
    0.07
    اوية
    0.07
     punctuation
    0.07
     Public
    0.07
    い
    0.07
     Druid
    0.06
    .SubElement
    0.06
    Act Density 0.006%

    No Known Activations