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

    Neuronpedia

    INDEX
    Explanations

    Timer

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -sensitive
    -0.08
     Sheldon
    -0.07
     vận
    -0.07
     하나
    -0.07
    leit
    -0.07
     오른
    -0.07
     Rij
    -0.07
    ières
    -0.07
     papar
    -0.07
     blush
    -0.07
    POSITIVE LOGITS
     मुफ्त
    0.11
     gratuitos
    0.10
     бесплат
    0.10
    免费下载
    0.09
     ücretsiz
    0.09
    免费的
    0.09
     ofreciendo
    0.09
     бесплатно
    0.09
     डाउनलोड
    0.09
     gratuitas
    0.08
    Act Density 0.001%

    No Known Activations