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

    Neuronpedia

    INDEX
    Explanations

    no

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    December
    -0.09
     fiscales
    -0.09
     fiscais
    -0.08
     heutzutage
    -0.08
     December
    -0.08
     February
    -0.08
     danas
    -0.08
     Farn
    -0.08
     fouten
    -0.08
     दिसंबर
    -0.08
    POSITIVE LOGITS
     всп
    0.09
    -established
    0.08
     ফিরে
    0.08
     intervenir
    0.08
     refuses
    0.07
     automáticamente
    0.07
     rápidamente
    0.07
    表现
    0.07
     intervention
    0.07
    -you
    0.07
    Act Density 0.168%

    No Known Activations