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

    Neuronpedia

    INDEX
    Explanations

    Calculations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     UIView
    -0.09
    луқ
    -0.07
     حب
    -0.07
    λού
    -0.07
     profiling
    -0.07
     caminos
    -0.07
     BJP
    -0.07
     lowu
    -0.07
     MSc
    -0.07
     carved
    -0.07
    POSITIVE LOGITS
     unfortunately
    0.09
     unsuitable
    0.09
    거나
    0.09
     sistèm
    0.09
     unrealistic
    0.09
     unacceptable
    0.08
    ịnh
    0.08
    Nein
    0.08
     leider
    0.08
    מער
    0.08
    Act Density 0.051%

    No Known Activations