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

    Neuronpedia

    INDEX
    Explanations

    code snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     financ
    -0.08
    Senator
    -0.07
     había
    -0.07
    _CN
    -0.07
     Honolulu
    -0.06
     Hari
    -0.06
     gå
    -0.06
     bluff
    -0.06
     бан
    -0.06
    λογία
    -0.06
    POSITIVE LOGITS
    ев
    0.07
    YD
    0.06
     Called
    0.06
    lood
    0.06
    	Address
    0.06
    ميل
    0.06
    _relation
    0.06
    мотр
    0.06
    -linked
    0.06
    engers
    0.06
    Act Density 0.000%

    No Known Activations