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

    Neuronpedia

    INDEX
    Explanations

    natural

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     tablet
    -0.07
     penny
    -0.06
    	location
    -0.06
    django
    -0.06
    amet
    -0.06
     reproduce
    -0.06
    (alias
    -0.06
     ανά
    -0.06
     FactoryBot
    -0.06
     verdad
    -0.06
    POSITIVE LOGITS
    _REGION
    0.08
    /km
    0.07
    .vs
    0.06
     %>
    0.06
     ►
    0.06
    itious
    0.06
            
    0.06
     ';↵
    0.06
    >User
    0.06
    ุส
    0.06
    Act Density 1.203%

    No Known Activations