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
     combustible
    -0.10
     nutritious
    -0.08
    เต
    -0.08
     Product
    -0.08
     aggregated
    -0.08
    �
    -0.08
     cough
    -0.08
     Buffet
    -0.08
     aggregates
    -0.08
     aggregation
    -0.08
    POSITIVE LOGITS
     transformation
    0.11
     transformations
    0.11
    	transform
    0.11
    Transformation
    0.10
     Transformation
    0.10
     symmetry
    0.10
     transform
    0.09
     symmetrical
    0.09
     transformación
    0.09
     symmetric
    0.09
    Act Density 0.027%

    No Known Activations