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

    Neuronpedia

    INDEX
    Explanations

    main

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    IFF
    -0.08
     mb
    -0.07
    NER
    -0.07
    ign
    -0.07
     Components
    -0.07
    otec
    -0.07
     injection
    -0.06
    escape
    -0.06
    MDB
    -0.06
    )],↵
    -0.06
    POSITIVE LOGITS
     exemp
    0.07
    MainFrame
    0.06
    _rem
    0.06
    :list
    0.06
    serializer
    0.06
    中华
    0.06
     realistic
    0.06
     اسم
    0.06
    	startActivity
    0.06
     distilled
    0.06
    Act Density 0.018%

    No Known Activations