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

    Neuronpedia

    INDEX
    Explanations

    examples

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     normalized
    0.63
     normalised
    0.61
    ریع
    0.60
     अधी
    0.59
    otropin
    0.57
    .([]
    0.57
     तैयारियां
    0.57
    alih
    0.56
    ชาติ
    0.56
    猷
    0.56
    POSITIVE LOGITS
     example
    2.89
    example
    2.76
     Example
    2.63
     ejemplo
    2.61
    Example
    2.61
     exemplo
    2.54
    示例
    2.50
     esempio
    2.45
    demo
    2.45
     examples
    2.45
    Act Density 0.718%

    No Known Activations