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
     accompanies
    -0.07
    равиль
    -0.06
    Issues
    -0.06
    [{
    -0.06
    VOID
    -0.06
     parody
    -0.06
     Bundle
    -0.06
     Kushner
    -0.06
    ittle
    -0.06
     sposób
    -0.06
    POSITIVE LOGITS
    ุทร
    0.07
     Sony
    0.07
    ��
    0.07
     defend
    0.06
    ницу
    0.06
     vitae
    0.06
    	sh
    0.06
    lint
    0.06
    uni
    0.06
    .optim
    0.06
    Act Density 0.001%

    No Known Activations