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

    Neuronpedia

    INDEX
    Explanations

    mathematical reasoning

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     objectively
    -0.10
     κορ
    -0.09
    ，对
    -0.09
     και
    -0.09
     وهل
    -0.08
     assessing
    -0.08
    Ү
    -0.08
     և
    -0.08
     تقييم
    -0.08
    Ά
    -0.08
    POSITIVE LOGITS
     constructions
    0.09
     cleverly
    0.08
     artificially
    0.08
     SOUR
    0.08
     reutil
    0.08
     construction
    0.08
    Construction
    0.08
     conseguimos
    0.08
     Fibonacci
    0.08
     artificial
    0.08
    Act Density 0.035%

    No Known Activations