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

    Neuronpedia

    INDEX
    Explanations

    complex math

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     preparing
    -0.09
     préparation
    -0.08
     preparação
    -0.08
     prepare
    -0.08
    Preparing
    -0.08
    Prepar
    -0.08
    Prepare
    -0.08
     prepara
    -0.08
     preparación
    -0.08
    Preparation
    -0.08
    POSITIVE LOGITS
     denominator
    0.11
     Ratio
    0.10
     знамен
    0.10
    Ratio
    0.09
    _ratio
    0.09
     Recipro
    0.09
    _RATIO
    0.09
     denomin
    0.09
     дроб
    0.09
    ratio
    0.09
    Act Density 0.057%

    No Known Activations