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

    Neuronpedia

    INDEX
    Explanations

    |

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     encompasses
    -0.08
     encompassing
    -0.08
     политики
    -0.08
     umfasst
    -0.08
    ностей
    -0.07
    /par
    -0.07
    .configure
    -0.07
    	Vec
    -0.07
    ı
    -0.07
    /connect
    -0.07
    POSITIVE LOGITS
    eo
    0.08
     Strawberry
    0.08
     �
    0.08
     Addiction
    0.08
     ბოლო
    0.08
    ongan
    0.08
     glän
    0.08
    هادة
    0.08
     hiervoor
    0.08
     earns
    0.08
    Act Density 0.035%

    No Known Activations